Tag: machine learning

Today's lenders use expanded data sources and advanced analytics to predict credit risk more accurately and optimize their lending and operations. The result may be a win-win for lenders and customers. What is credit risk? Credit risk is the possibility that a borrower will not repay a debt as agreed. Credit risk management encompasses the policies, tools and systems that lenders use to understand this risk. These can be important throughout the customer lifecycle, from marketing and sending preapproved offers to underwriting and portfolio management. Poor risk management can lead to unnecessary losses and missed opportunities, especially because risk departments need to manage risk with their organization's budgetary, technical and regulatory constraints in mind. How is it assessed?  Credit risk is often assessed with credit risk analytics — statistical modeling that predicts the risk involved with credit lending. Lenders may create and use credit risk models to help drive decisions. Additionally (or alternatively), they rely on generic or custom credit risk scores: Generic scores: Analytics companies create predictive models that rank order consumers based on the likelihood that a person will fall 90 or more days past due on any credit obligation in the next 24 months. Lenders can purchase these risk scores to help them evaluate risk. Custom scores: Custom credit risk modeling solutions help organizations tailor risk scores for particular products, markets, and customers. Custom scores can incorporate generic risk scores, traditional credit data, alternative credit data* (or expanded FCRA-regulated data), and a lender's proprietary data to increase their effectiveness. About 41 percent of consumer lending organizations use a model-first approach, and 55 percent use a score-first approach to credit decisioning.1 However, these aren't entirely exclusive groupings. For example, a credit score may be an input in a lender's credit risk model — almost every lender (99 percent) that uses credit risk models for decisioning also uses credit scores.2 Similarly, lenders that primarily rely on credit scores may also have business policies that affect their decisions. What are the current challenges? Risk departments and teams are facing several overarching challenges today: Staying flexible: Volatile market conditions and changing consumer preferences can lead to unexpected shifts in risk. Organizations need to actively monitor customer accounts and larger economic trends to understand when, if, and how they should adjust their risk policies. Digesting an overwhelming amount of data: More data can be beneficial, but only if it offers real insights and the organization has the resources to understand and use it efficiently. Artificial intelligence (AI) and machine learning (ML) are often important for turning raw data into actionable insights. Retaining IT talent: Many organizations are trying to figure out how to use vast amounts of data and AI/ML effectively. However, 82 percent of lenders have trouble hiring and retaining data scientists and analysts.3 Separating fraud and credit losses: Understanding a portfolio's credit losses can be important for improving credit risk models and performance. But some organizations struggle to properly distinguish between the two, particularly when synthetic identity fraud is involved. Best practices for credit risk management Leading financial institutions have moved on from legacy systems and outdated risk models or scores. And they're looking at the current challenges as an opportunity to pull away from the competition. Here's how they're doing it: Using additional data to gain a holistic picture: Lenders have an opportunity to access more data sources, including credit data from alternative financial services and consumer-permissioned data. When combined with traditional credit data, credit scores, and internal data, the outcome can be a more complete picture of a consumer's credit risk. Implementing AI/ML-driven models: Lenders can leverage AI/ML to analyze large amounts of data to improve organizational efficiency and credit risk assessments. 16 percent of consumer lending organizations expect to solely use ML algorithms for credit decisioning, while two-thirds expect to use both traditional and ML models going forward.4 Increasing model velocity: On average, it takes about 15 months to go from model development to deployment. But some organizations can do it in less than six.5 Increasing model velocity can help organizations quickly respond to changing consumer and economic conditions. Even if rapid model creation and deployment isn't an option, monitoring model health and recalibrating for drift is important. Nearly half (49 percent) of lenders check for model drift monthly or quarterly — one out of ten get automated alerts when their models start to drift.6 WATCH: Accelerating Model Velocity in Financial Institutions Improving automation and customer experience Lenders are using AI to automate their application, underwriting, and approval processes. Often, automation and ML-driven risk models go hand-in-hand. Lenders can use the models to measure the credit risk of consumers who don't qualify for traditional credit scores and automation to expedite the review process, leading to an improved customer experience. Learn more by exploring Experian's credit risk solutions. Learn more * When we refer to “Alternative Credit Data," this refers to the use of alternative data and its appropriate use in consumer credit lending decisions as regulated by the Fair Credit Reporting Act (FCRA). Hence, the term “Expanded FCRA Data" may also apply in this instance and both can be used interchangeably. 1-6. Experian (2023). Accelerating Model Velocity in Financial Institutions

Model governance is growing increasingly important as more companies implement machine learning model deployment and AI analytics solutions into their decision-making processes. Models are used by institutions to influence business decisions and identify risks based on data analysis and forecasting. While models do increase business efficiency, they also bring their own set of unique risks. Robust model governance can help mitigate these concerns, while still maintaining efficiency and a competitive edge. What is model governance? Model governance refers to the framework your organization has in place for overseeing how you manage your development, model deployment, validation and usage.1 This can involve policies like who has access to your models, how they are tested, how new versions are rolled out or how they are monitored for accuracy and bias.2 Because models analyze data and hypotheses to make predictions, there's inherent uncertainty in their forecasts.3 This uncertainty can sometimes make them vulnerable to errors, which makes robust governance so important. Machine learning model governance in banks, for example, might include internal controls, audits, a thorough inventory of models, proper documentation, oversight and ensuring transparent policies and procedures. One significant part of model governance is ensuring your business complies with federal regulations. The Federal Reserve Board and the Office of the Comptroller of the Currency (OCC) have published guidance protocols for how models are developed, implemented and used. Financial institutions that utilize models must ensure their internal policies are consistent with these regulations. The OCC requirements for financial institutions include: Model validations at least once a year Critical review by an independent party Proper model documentation Risk assessment of models' conceptual soundness, intended performance and comparisons to actual outcomes Vigorous validation procedures that mitigate risk Why is model governance important — especially now? More and more organizations are implementing AI, machine learning and analytics into their models. This means that in order to keep up with the competition's efficiency and accuracy, your business may need complex models as well. But as these models become more sophisticated, so does the need for robust governance.3 Undetected model errors can lead to financial loss, reputation damage and a host of other serious issues. These errors can be introduced at any point from design to implementation or even after deployment via inappropriate usage of the model, drift or other issues. With model governance, your organization can understand the intricacies of all the variables that can affect your models' results, controlling production closely with even greater efficiency and accuracy. Some common issues that model governance monitors for include:2 Testing for drift to ensure that accuracy is maintained over time. Ensuring models maintain accuracy if deployed in new locations or new demographics. Providing systems to continuously audit models for speed and accuracy. Identifying biases that may unintentionally creep into the model as it analyzes and learns from data. Ensuring transparency that meets federal regulations, rather than operating within a black box. Good model governance includes documentation that explains data sources and how decisions are reached. Model governance use cases Below are just three examples of use cases for model governance that can aid in advanced analytics solutions. Credit scoring A credit risk score can be used to help banks determine the risks of loans (and whether certain loans are approved at all). Governance can catch biases early, such as unintentionally only accepting lower credit scores from certain demographics. Audits can also catch biases for the bank that might result in a qualified applicant not getting a loan they should. Interest rate risk Governance can catch if a model is making interest rate errors, such as determining that a high-risk account is actually low-risk or vice versa. Sometimes changing market conditions, like a pandemic or recession, can unintentionally introduce errors into interest rate data analysis that governance will catch. Security challenges One department in a company might be utilizing a model specifically for their demographic to increase revenue, but if another department used the same model, they might be violating regulatory compliance.4 Governance can monitor model security and usage, ensuring compliance is maintained. Why Experian? Experian® provides risk mitigation tools and objective and comprehensive model risk management expertise that can help your company implement custom models, achieve robust governance and comply with any relevant federal regulations. In addition, Experian can provide customized modeling services that provide unique analytical insights to ensure your models are tailored to your specific needs. Experian's model risk governance services utilize business consultants with tenured experience who can provide expert independent, third-party reviews of your model risk management practices. Key services include: Back-testing and benchmarking: Experian validates performance and accuracy, including utilizing statistical metrics that compare your model's performance to previous years and industry benchmarks. Sensitivity analysis: While all models have some degree of uncertainty, Experian helps ensure your models still fall within the expected ranges of stability. Stress testing: Experian's experts will perform a series of characteristic-level stress tests to determine sensitivity to small changes and extreme changes. Gap analysis and action plan: Experts will provide a comprehensive gap analysis report with best-practice recommendations, including identifying discrepancies with regulatory requirements. Traditionally, model governance can be time-consuming and challenging, with numerous internal hurdles to overcome. Utilizing Experian's business intelligence and analytics solutions, alongside its model risk management expertise, allows clients to seamlessly pass requirements and experience accelerated implementation and deployment. Experian can optimize your model governance Experian is committed to helping you optimize your model governance and risk management. Learn more here. References 1Model Governance," Open Risk Manual, accessed September 29, 2023. https://www.openriskmanual.org/wiki/Model_Governance2Lorica, Ben, Doddi, Harish, and Talby, David. "What Are Model Governance and Model Operations?" O'Reilly, June 19, 2019. https://www.oreilly.com/radar/what-are-model-governance-and-model-operations/3"Comptroller's Handbook: Model Risk Management," Office of the Comptroller of the Currency. August 2021. https://www.occ.treas.gov/publications-and-resources/publications/comptrollers-handbook/files/model-risk-management/pub-ch-model-risk.pdf4Doddi, Harish. "What is AI Model Governance?" Forbes. August 2, 2021. https://www.forbes.com/sites/forbestechcouncil/2021/08/02/what-is-ai-model-governance/?sh=5f85335f15cd

Data-driven machine learning model development is a critical strategy for financial institutions to stay ahead of their competition, and according to IDC, remains a strategic priority for technology buyers.  Improved operational efficiency, increased innovation, enhanced customer experiences and employee productivity are among the primary business objectives for organizations that choose to invest in artificial intelligence (AI) and machine learning (ML), according to IDC’s 2022 CEO survey.   While models have been around for some time, the volume of models and scale at which they are utilized has proliferated in recent years. Models are also now appearing in more regulated aspects of the business, which demand increased scrutiny and transparency.   Implementing an effective model development process is key to achieving business goals and complying with regulatory requirements. While ModelOps, the governance and life cycle management of a wide range of operationalized AI models, is becoming more popular, most organizations are still at relatively low levels of maturity. It's important for key stakeholders to implement best practices and accelerate the model development and deployment lifecycle.   Read the IDC Spotlight Challenges impeding machine learning model development  Model development involves many processes, from wrangling data, analysis, to building a model that is ready for deployment, that all need to be executed in a timely manner to ensure proper outcomes. However, it is challenging to manage all these processes in today’s complex environment.   Modeling challenges include:  Infrastructure: Necessary factors like storage and compute resources incur significant costs, which can keep organizations from evolving their machine learning capabilities.   Organizational: Implementing machine learning applications requires talent, like data scientists and data and machine learning engineers.  Operational: Piece meal approaches to ML tools and technologies can be cumbersome, especially on top of data being housed in different places across an organization, which can make pulling everything together challenging.  Opportunities for improvement are many While there are many places where individuals can focus on improving model development and deployment, there are a few key places where we see individuals experiencing some of the most time-consuming hang-ups.   Data wrangling and preparation   Respondents to IDC's 2022 AI StrategiesView Survey indicated that they spend nearly 22% of their time collecting and preparing data. Pinpointing the right data for the right purpose can be a big challenge. It is important for organizations to understand the entire data universe and effectively link external data sources with their own primary first party data. This way, stakeholders can have enough data that they trust to effectively train and build models.   Model building  While many tools have been developed in recent years to accelerate the actual building of models, the volume of models that often need to be built can be difficult given the many conflicting priorities for data teams within given institutions. Where possible, it is important for organizations to use templates or sophisticated platforms to ease the time to build a model and be able to repurpose elements that may already be working for other models within the business.   Improving Model Velocity Experian’s Ascend ML BuilderTM is an on-demand advanced model development environment optimized to support a specific project. Features include a dedicated environment, innovative compute optimization, pre-built code called ‘Accelerators’ that simply, guide, and speed data wrangling, common analyses and advanced modeling methods with the ability to add integrated deployment.  To learn more about Experian’s Ascend ML Builder, click here.   To read the full Technology Spotlight, download “Accelerating Model Velocity with a Flexible Machine Learning Model Development Environment for Financial Institutions” here.  Download spotlight *This article includes content created by an AI language model and is intended to provide general information. 

From science fiction-worthy image generators to automated underwriting, artificial intelligence (AI), big data sets and advances in computing power are transforming how we play and work. While the focus in the lending space has often been on improving the AI models that analyze data, the data that feeds into the models is just as important. Enter: data-centric AI. What is a data-centric AI? Dr. Andrew Ng, a leader in the AI field, advocates for data-centric AI and is often credited with coining the term. According to Dr. Ng, data-centric AI is, ‘the discipline of systematically engineering the data used to build an AI system.’1 To break down the definition, think of AI systems as a combination of code and data. The code is the model or algorithm that analyzes data to produce a result. The data is the information you use to train the model or later feed into the model to request a result. Traditional approaches to AI focus on the code — the models. Multiple organizations download and use the same data sets to create and improve models. But today, continued focus on model development may offer a limited return in certain industries and use cases. A data-centric AI approach focuses on developing tools and practices that improve the data. You may still need to pay attention to model development but no longer treat the data as constant. Instead, you try to improve a model's performance by increasing data quality. This can be achieved in different ways, such as using more consistent labeling, removing noisy data and collecting additional data.2 Data-centric AI isn't just about improving data quality when you build a model — it's also part of the ongoing iterative process. The data-focused approach should continue during post-deployment model monitoring and maintenance. Data-centric AI in lending Organizations in multiple industries are exploring how a data-centric approach can help them improve model performance, fairness and business outcomes. For example, lenders that take a data-centric approach to underwriting may be able to expand their lending universe, drive growth and fulfill financial inclusion goals without taking on additional risk. Conventional credit scoring models have been trained on consumer credit bureau data for decades. New versions of these models might offer increased performance because they incorporate changes in the economic landscape, consumer behavior and advances in analytics. And some new models are built with a more data-centric approach that considers additional data points from the existing data sets — such as trended data — to score consumers more accurately. However, they still solely rely on credit bureau data. Explainability and transparency are essential components of responsible AI and machine learning (a type of AI) in underwriting. Organizations need to be able to explain how their models come to decisions and ensure they are behaving as expected. Model developers and lenders that use AI to build credit risk models can incorporate new high-quality data to supplement existing data sets. Alternative credit data can include information from alternative financial services, public records, consumer-permissioned data, and buy now, pay later (BNPL) data that lenders can use in compliance with the Fair Credit Reporting Act (FCRA).* The resulting AI-driven models may more accurately predict credit risk — decreasing lenders' losses. The models can also use alternative credit data to score consumers that conventional models can't score. Infographic: From initial strategy to results — with stops at verification, decisioning and approval — see how customers travel across an Automated Loan Underwriting Journey. Business benefit of using data-centric AI models Financial services organizations can benefit from using a data-centric AI approach to create models across the customer lifecycle. That may be why about 70 percent of businesses frequently discuss using advanced analytics and AI within underwriting and collections.3 Many have gone a step further and implemented AI. Underwriting is one of the main applications for machine learning models today, and lenders are using machine learning to:4 More accurately assess credit risk models. Decrease model development, deployment and recalibration timelines. Incorporate more alternative credit data into credit decisioning. AI analytics solutions may also increase customer lifetime value by helping lenders manage credit lines, increase retention, cross-sell products and improve collection efforts. Additionally, data-centric AI can assist with fraud detection and prevention. Case study: Learn how Atlas Credit, a small-dollar lender, used a machine learning model and loan automation to nearly doubled its loan approval rates while decreasing its credit risk losses. How Experian helps clients leverage data-centric AI for better business outcomes During a presentation in 2021, Dr. Ng used the 80-20 rule and cooking as an analogy to explain why the shift to data-centric AI makes sense.5 You might be able to make an okay meal with old or low-quality ingredients. However, if you source and prepare high-quality ingredients, you're already 80% of the way toward making a great meal. Your data is the primary ingredient for your model — do you want to use old and low-quality data? Experian has provided organizations with high-quality consumer and business credit solutions for decades, and our industry-leading data sources, models and analytics allow you to build models and make confident decisions. If you need a sous-chef, Experian offers services and has data professionals who can help you create AI-powered predictive analytics models using bureau data, alternative data and your in-house data. Learn more about our AI analytics solutions and how you can get started today. 1DataCentricAI. (2023). Data-Centric AI.2Exchange.scale (2021). The Data-Centric AI Approach With Andrew Ng.3Experian (2021). Global Insights Report September/October 2021.4FinRegLab (2021). The Use of Machine Learning for Credit Underwriting: Market & Data Science Context. 5YouTube (2021). A Chat with Andrew on MLOps: From Model-Centric to Data-Centric AI *Disclaimer: When we refer to “Alternative Credit Data," this refers to the use of alternative data and its appropriate use in consumer credit lending decisions, as regulated by the Fair Credit Reporting Act. Hence, the term “Expanded FCRA Data" may also apply in this instance and both can be used interchangeably.

The Federal Reserve (Fed) took a big step towards revolutionizing the U.S. payment landscape with the official launch of FedNow, a new instant payment service, on July 20, 2023. While the new payment network offers advantages, there are concerns that fraudsters may be quick to exploit the new real-time technology with fraud schemes like automated push payment (APP) fraud. How is FedNow different from existing payment networks? To keep pace with regions across the globe and accelerate innovation, the U.S. created a alternative to the existing payment network known as The Clearing House (TCH) Real-Time Payment Network (RTP). Fraudsters can use the fact that real-time payments immediately settle to launder the stolen money through multiple channels quickly. The potential for this kind of fraud has led financial regulators to consider measures to better protect against it. While both FedNow and RTP charge a comparable fee of 4.5 cents per originated transaction, the key distinction lies in their governance. RTP is operated by a consortium of large banks, whereas FedNow falls under the jurisdiction of the Federal Reserve Bank. This distinction could give FedNow an edge in the market. One of the advantages of FedNow is its integration with the extensive Federal Reserve network, allowing smaller local banks across the country to access the service. RTP estimates accessibility to institutions holding approximately 90% of U.S. demand deposit accounts (DDAs), but currently only reaches 62% of DDAs due to limited participation from eligible institutions. What are real-time payments? Real-time payments refer to transactions between bank accounts that are initiated, cleared, and settled within seconds, regardless of the time or day. This immediacy enhances transparency and instills confidence in payments, which benefits consumers, banks and businesses.Image sourced from JaredFranklin.com Real-time payments have gained traction globally, with adoptions from over 70 countries on six continents. In 2022 alone, these transactions amounted to a staggering $195 billion, representing a remarkable year-over-year growth of 63%. India leads the pack with its Unified Payments Interface platform, processing a massive $89.5 billion in transaction volume. Other significant markets include Brazil, China, Thailand, and South Korea. The fact that real-time payments cannot be reversed promotes trust and ensures that contracts are upheld. This also encourages the development of new methods to make processes more efficient, like the ability to pay upon receiving the goods or services. These advancements are particularly crucial for small businesses, which disproportionately bear the burden of delayed payments, amounting to a staggering $3 trillion globally at any given time. The launch of FedNow marks a significant milestone in the U.S. financial landscape, propelling the country towards greater efficiency, transparency, and innovation in payments. However, it also brings a fair share of challenges, including the potential for increased fraud. Are real-time payments a catalyst for fraud? As the financial landscape evolves with the introduction of real-time payment systems, fraudsters are quick to exploit new technologies. One particular form of fraud that has gained prominence is authorized push payment (APP) fraud. APP fraud is a type of scam where fraudsters trick individuals or businesses into authorizing the transfer of funds from their bank accounts to accounts controlled by the fraudsters. The fraudster poses as a legitimate entity and deceives the victim into believing that there is an urgent need to transfer money. They gain the victim's trust and provide instructions for the transfer, typically through online or telephone banking channels. The victim willingly performs the payment, thinking it is legitimate, but realizes they have been scammed when communication halts. APP fraud is damaging as victims authorize the payments themselves, making it difficult for banks to recover the funds. To protect against APP fraud, it's important to be cautious, verify the legitimacy of requests independently, and report any suspicious activity promptly. Fraud detection and prevention with real-time payments Advances in fraud detection software, including machine learning and behavioral analytics, make unusual urgent requests and fake invoices easier to spot — in real time — but some governments are considering legislation to ensure more support for victims. For example, in the U.K., frameworks like Confirmation of Payee have rolled out instant account detail checks against the account holder’s name to help prevent cases of authorized push payment fraud. The U.K.’s real-time payments scheme Pay.UK also introduced the Mule Insights Tactical Solution (MITS), which tracks the flow of fraudulent transactions used in money laundering through bank and credit union accounts. It identifies these accounts and stops the proceeds of crimes from moving deeper into the system – and can help victims recover their funds. While fraud levels related to traditional payments have slowly come down, real-time payment-related fraud has recently skyrocketed. India, one of the primary innovators in the space, recorded a 23% rise in fraud related to its real-time payments system in 2022. The same ACI report stated that the U.S., making up only 1.2% of all real-time payment transactions in 2022, had, for now, avoided the effects. However, “there is no reason to assume that without action, the U.S. will not follow the path to crisis levels of APP scams as seen in other markets.” FedNow currently has no specific plans to bake fraud detection into their newly launched technology, meaning the response is left to financial institutions. Fight instant fraud with instant answers Artificial Intelligence (AI) holds tremendous potential in combating the ever-present threat of fraud. With AI technologies, financial institutions can process vast amounts of data points faster and enhance their fraud detection capabilities. This enables them to identify and flag suspicious transactions that deviate from the norm, mitigating identity risk and safeguarding customer accounts. The ability of AI-powered systems to ingest and analyze real-time information empowers institutions to stay one step ahead in the battle against account takeover fraud. This type of fraud, which poses a significant challenge to real-time payment systems, can be better addressed through AI-enabled tools. With ongoing monitoring of account behavior, such as the services provided by FraudNet, financial institutions gain a powerful weapon against APP fraud. In addition to behavioral analysis, location data has emerged as an asset in the fight against fraud. Incorporating location-based information into fraud detection algorithms has proven effective in pinpointing suspicious activities and reducing fraudulent incidents. As the financial industry continues to grapple with the constant evolution of fraud techniques, harnessing the potential of AI, coupled with comprehensive data analysis and innovative technologies, becomes crucial for securing the integrity of financial transactions. Taking your next step in the fight against fraud Ultimately, the effectiveness of fraud prevention measures depends on the implementation and continuous improvement of security protocols by financial institutions, regulators, and technology providers. By staying vigilant and employing appropriate safeguards, fraud risks in real-time payment systems, such as FedNow, can be minimized. To learn more about how Experian can help you leverage fraud prevention solutions, visit us online or request a call.  *This article leverages/includes content created by an AI language model and is intended to provide general information.

Using data to understand risk and make lending decisions has long been a forte of leading financial institutions. Now, with artificial intelligence (AI) taking the world by storm, lenders are finding innovative ways to improve their analytical capabilities. How AI analytics differs from traditional analytics Data analytics is analyzing data to find patterns, relationships and other insights. There are four main types of data analytics: descriptive, diagnostic, predictive and prescriptive. In short, understanding the past and why something happened, predicting future outcomes and offering suggestions based on likely outcomes. Traditionally, data analysts and scientists build models and help create decisioning strategies to align with business needs. They may form a hypothesis, find and organize relevant data and then run analytics models to test their hypothesis. However, time and resource constraints can limit the traditional analytics approach. As a result, there might be a focus on answering a few specific questions: Will this customer pay their bills on time? How did [X] perform last quarter? What are the chances of [Y] happening next year? AI analytics isn't completely different — think of it as a complementary improvement rather than a replacement. It relies on advances in computing power, analytics techniques and different types of training to create models more efficient than traditional analytics. By leveraging AI, companies can automate much of the data gathering, cleaning and analysis, saving them time and money. The AI models can also answer more complex questions and work at a scale that traditional analytics can't keep up with. Advances in AI are additionally offering new ways to use and interact with data. Organizations are already experimenting with using natural language processing and generative AI models. These can help even the most non-technical employees and customers to interact with vast amounts of data using intuitive and conversational interfaces. Benefits of AI analytics The primary benefits of AI-driven analytics solutions are speed, scale and the ability to identify more complex relationships in data. Speed: Where traditional analytics might involve downloading and analyzing spreadsheets to answer a single question, AI analytics automates these processes – and many others.Scale: AI analytics can ingest large amounts of data from multiple data sources to find analytical insights that traditional approaches may miss. When combined with automation and faster processing times, organizations can scale AI analytics more efficiently than traditional analytics.Complexity: AI analytics can answer ambiguous questions. For example, a marketing team may use traditional analytics to segment customers by known characteristics, such as age or location. But they can use AI analytics to find segments based on undefined shared traits or interests, and the results could include segments that they wouldn't have thought to create on their own. The insights from data analytics might be incorporated into a business intelligence platform. Traditionally, data analysts would upload reports or update a dashboard that business leaders could use to see the results and make educated decisions. Modern business intelligence and analytics solutions allow non-technical business leaders to analyze data on their own. With AI analytics running in the background, business leaders can quickly and easily create their own reports and test hypotheses. The AI-powered tools may even be able to learn from users' interactions to make the results more relevant and helpful over time. WATCH: See how organizations are using business intelligence to unlock better lending decisions with expert insights and a live demo. Using AI analytics to improve underwriting From global retailers managing supply chains to doctors making life-changing diagnoses, many industries are turning to AI analytics to make better data-driven decisions. Within financial services, there are significant opportunities throughout customer lifecycles. For example, some lenders use machine learning (ML), a subset of AI, to help create credit risk models that estimate the likelihood that a borrower will miss a payment in the future. Credit risk models aren't new — lenders have used models and credit scores for decades. However, ML-driven models have been able to outperform traditional credit risk models by up to 15 percent.1 In part, this is because the machine learning models might use traditional credit data and alternative credit data* (or expanded FCRA-regulated data), including information from alternative financial services and buy now pay later loans. They can also analyze the vast amounts of data to uncover predictive attributes that logistic regression (a more traditional approach) models might miss. The resulting ML models can score more consumers than traditional models and do so more accurately. Lenders that use these AI-driven models may be able to expand their lending universe and increase automation in their underwriting process without taking on additional risk. However, lenders may need to use a supervised learning approach to create explainable models for credit underwriting to comply with regulations and ensure fair lending practices. Read: The Explainability: ML and AI in credit decisioning report explores why ML models will become the norm, why explainability is important and how to use machine learning. Experian helps clients use AI analytics Although AI analytics can lead to more productive and efficient analytics operations over time, the required upfront cost or expertise may be prohibitive for some organizations. But there are simple solutions. Built with advanced analytics, our Lift Premium™ scoring model uses traditional and alternative credit data to score more consumers than conventional scoring models. It can help organizations increase approvals among thin-file and credit-invisible consumers, and more accurately score thick-file consumers.2 Experian can also help you create, test, deploy and monitor AI models and decisioning strategies in a collaborative environment. The models can be trained on Experian's vast data sources and your internal data to create a custom solution that improves your underwriting accuracy and capabilities. Learn more about machine learning and AI analytics. * When we refer to “Alternative Credit Data," this refers to the use of alternative data and its appropriate use in consumer credit lending decisions as regulated by the Fair Credit Reporting Act (FCRA). Hence, the term “Expanded FCRA Data" may also apply in this instance and both can be used interchangeably. 1. Experian (2020). Machine Learning Decisions in Milliseconds 2. Experian (2022). Lift PremiumTM product sheet

Machine learning (ML) is a powerful tool that can consume vast amounts of data to uncover patterns, learn from past behaviors, and predict future outcomes. By leveraging ML-powered credit risk models, lenders can better determine the likelihood that a consumer will default on a loan or credit obligation, allowing them to score applicants more accurately. When applied to credit decisioning, lenders can achieve a 25 percent reduction in exposure to risky customers and a 35 percent decrease in non-performing loans.1 While ML-driven models enable lenders to target the right audience and control credit losses, many organizations face challenges in developing and deploying these models. Some still rely on traditional lending models with limitations preventing them from making fast and accurate decisions, including slow reaction times, fewer data sources, and less predictive performance. With a trusted and experienced partner, financial institutions can create and deploy highly predictive ML models that optimize their credit decisioning. Case study: Increase customer acquisition with improved predictive performance Looking to meet growth goals without increasing risk, a consumer goods retailer sought out a modern and flexible solution that could help expand its finance product options. This meant replacing existing ML models with a custom model that offers greater transparency and predictive power. The retailer partnered with Experian to develop a transparent and explainable ML model. Based on the model’s improved predictive performance, transparency, and ability to derive adverse action reasons for declines, the retailer increased sales and application approval rates while reducing credit risk. Read the case study Learn about our custom modeling capabilities 1 Experian (2020). The Art of Decisioning in Uncertain Times

E-commerce digital transactions are rapidly increasing as online shopping becomes more convenient. In fact, a recent survey found that 75% of large and mid-sized U.S. businesses expect double-digit ecommerce growth through the end of the year, indicating that online purchases are not slowing down. As a result, opportunities for fraudsters to exploit businesses and consumers for monetary gain are reaching high levels. Businesses must be aware of the risks associated with card not present (CNP) fraud and take steps to protect themselves and their customers. What is card not present fraud? Card not present fraud refers to fraudulent activity that occurs when a criminal uses a stolen or compromised credit card to make a purchase online, over the phone, or through some other means where the card is not physically present at the time of the transaction. This type of fraud can be particularly difficult to detect and prevent, as it relies on the use of stolen card information rather than the physical card itself. Because CNP fraud can yield significant losses for businesses, many have adopted various fraud prevention and identity resolution and verification tools to better manage risk and prevent fraud losses. Since much of the success or failure of e-commerce depends on how easy merchants make it for consumers to complete a transaction, incorporating CNP fraud prevention and identity verification tools in the checkout process should not come at the expense of completing transactions for legitimate customers. What do we mean by that? Let’s look at false declines. What is a false decline? False declines occur when legitimate transactions are mistakenly declined due to the business's fraud detection system incorrectly flagging the transaction as potentially fraudulent. This can be frustrating for cardholders and can lead to lost sales for merchants. A recent report found that the average false declines rate is 1.16 percent, and if you consider that there was over $960 billion in U.S. online sales in 2021, the potential for loss is significant. The consequences of CNP fraud and false declines can be severe for businesses. In the case of CNP fraud, businesses may lose the sale and also be on the hook for any charges that result from the fraudulent activity. False declines, on the other hand, can result in lost sales and damage to the business's reputation with customers. In either case, it is important for businesses to have measures in place to mitigate the risks of both. How can online businesses increase sales without compromising their fraud defense? One way to mitigate the risk of CNP fraud is to implement additional security measures at the time of transaction. This can include requiring additional verification information, such as a CVV code or a billing zip code to further authenticate the card holder’s identity. These measures can help to reduce the risk of CNP fraud by making it more difficult for fraudsters to complete a transaction. Machine learning algorithms can help analyze transaction data and identify patterns indicating fraudulent activity. These algorithms can be trained on historical data to learn what types of transactions are more likely to be fraudulent and then be used to flag potentially fraudulent transactions before it occurs. Businesses require data and technology that raise confidence in a shopper’s identity. Currently, the data merchants receive to approve transactions is not enough. A credit card owner verification solution like Experian Link fills this gap by enabling online businesses to augment their real-time decisions with data that links customer identity to the credit card being presented for payment to help verify the legitimacy of a transaction. Using Experian Link, businesses can link names, addresses and other identity markers to the customer’s credit card. The additional data enables better decisions, increased sales, decreased costs, a better buyer experience and better fraud detection. Get started with Experian Link™ - our frictionless credit card owner verification solution. Learn more

From chatbots to image generators, artificial intelligence (AI) has captured consumers' attention and spurred joy — and sometimes a little fear. It's not too different in the business world. There are amazing opportunities and lenders are increasingly turning to AI-driven lending decision engines and processes. But there are also open questions about how AI can work within existing regulatory requirements, how new regulations will impact its use and how to implement advanced analytics in a way that increases equitable inclusion rather than further embedding disparities. How are lenders using AI today? Many financial institutions have embraced — or at least tested — AI within several parts of their organization. The most advanced use of machine learning (ML) models tends to occur with credit card and unsecured personal loan underwriting.1 However, by late 2021, nearly three-quarters of businesses had used AI and machine learning, and 81 percent felt confident in using advanced analytics and AI in credit risk decisioning.2 READ MORE: AI and Machine Learning for Financial Institutions Today, lenders are implementing AI-driven tools throughout the customer lifecycle to: Target the right consumers: Lenders can sift through vast amounts of data to find consumers who match their credit criteria and send right-sized offers, which enables them to maximize their acceptance rates.Detect and prevent fraud:  Fraud detection tools have used AI and machine learning techniques to detect and prevent fraud for years. These systems may be even more important as fraudsters invest in technology and conduct increasingly sophisticated attacks.Assess creditworthiness: Machine learning-based models can incorporate a range of internal and external data points to more precisely evaluate creditworthiness and create a 10 to 15 percent performance lift compared with traditional linear and logistic regression models.3Automate decisions:  More precise evaluations can increase how many applications flow into your automated approval and denial process rather than requiring a manual review.Manage portfolios: Lenders can also use a more complete picture of their current customers to make better decisions. For example, AI-driven models can help lenders set initial credit limits and suggest when a change could help them increase wallet share or reduce risk. Lenders can also use AI to help determine which up- and cross-selling offers to present and when (and how) to reach out.Improve collections: Models can be built to ease debt collection processes, such as choosing where to assign accounts, which accounts to prioritize and how to contact the consumer. Additionally, businesses around the world have recognized improving customer acquisition and digital engagement as top priorities. In a recent Experian survey, companies ranked investing in AI second, behind investing in decisioning software, as the best way to improve their digital experiences.2 The benefits of AI in lending Although lenders can use machine learning models in many ways, the primary drivers for adoption in underwriting are:1 Improving credit risk assessmentFaster development and deployment cycles for new or recalibrated modelsUnlocking the possibilities within large datasetsKeeping up with competing lenders Some of the use cases for machine learning solutions have a direct impact on the bottom line — improving credit risk assessment can decrease charge-offs. Others are less direct but still meaningful. For instance, machine learning models might increase efficiency and allow further automation. This takes the pressure off your underwriting team, even when application volume is extremely high, and results in faster decisions for applicants, which can improve your customer experience. CASE STUDY:  Atlas Credit, a small-dollar lender, used a machine learning-powered model and automation to nearly double its loan approval rates and decrease credit losses by up to 20 percent. Incorporating large data sets into their decisions also allows lenders to expand their lending universe without taking on additional risk. For example, they may now be able to offer risk-appropriate credit lines to consumers that traditional scoring models can't score. And machine learning solutions can increasecustomer lifetime value when they're incorporated throughout the customer lifecycle by stopping fraud, improving retention, increasing up- or cross-selling and streamlining collections. Hurdles to adoption of machine learning in lending There are clear benefits and interest in machine learning and analytics, but adoption can be difficult, especially within credit underwriting. In August 2021, Forrester Consulting conducted a study commissioned by Experian and found the main barriers to adopting machine learning were:4 Explainability of machine learning models (35 percent)Model deployment into decisioning strategy management systems (34 percent)Model deployment into live operational runtime environment (31 percent)Lack of access to in-house transactional data (30 percent)Lack of access to a wide range of traditional and non-traditional data assets (30 percent) Explainability comes down to transparency and trust. Financial institutions have to trust that machine learning models will continue to outperform traditional models to make them a worthwhile investment. The models also have to be transparent and explainable for financial institutions to meet regulatory fair lending requirements.1 WATCH:  Explainable Artificial Intelligence: The Case of Fair Lending A lack of resources and expertise could hinder model development and deployment. It can take around nine months to build and deploy a custom model, and there's a lot of overhead to cover during the process.5 Large lenders might have in-house credit modeling teams that can take on the workload, but they also face barriers when integrating new models into legacy systems. Small- and mid-sized institutions may be more nimble, but they rarely have the in-house expertise to build or deploy models on their own. The models also have to be trained on appropriate data sets. Similar to model building and deployment, organizations might not have the human or financial resources to clean and organize internal data. And although vendors offer access to a lot of external data, sometimes sorting through and using the data requires a large commitment. How Experian is shaping the future of AI in lending Lenders are finding new ways to use AI throughout the customer lifecycle and with varying types of financial products. However, while the cost to create custom machine learning models is dropping, the complexities and unknowns are still too great for some lenders to manage. But that's changing.5 Experian built the Ascend Intelligence Services™ to help smaller and mid-market lenders access the most advanced analytics tools. The managed service platform won a Fintech Breakthrough Award in 2021, and it can significantly reduce the cost and deployment time for lenders who want to incorporate AI-driven strategies and machine learning models into their lending process. The end-to-end managed analytics service gives lenders access to Experian's vast data sets and can incorporate internal data to build and seamlessly deploy custom machine learning models. The platform can also continually monitor and retrain models to increase lift, and there's no “black box" to obscure how the model works. Everything is fully explainable, and the platform bakes regulatory constraints into the data curation and model development to ensure lenders stay compliant.5 Learn more about our machine learning solutions. * When we refer to “Alternative Credit Data," this refers to the use of alternative data and its appropriate use in consumer credit lending decisions as regulated by the Fair Credit Reporting Act (FCRA). Hence, the term “Expanded FCRA Data" may also apply in this instance and both can be used interchangeably. 1FinRegLab (2021). The Use of Machine Learning for Credit Underwriting: Market & Data Science Context2Experian (2021). Global Insights Report September/October 2021 3Experian (2020). Machine Learning Decisions in Milliseconds 4Experian (2022). Explainability: ML and AI in credit decisioning 5Experian (2021). Podcast: Advanced Analytics, Artificial Intelligence and Machine Learning in Lending

At Experian, we know that financial institutions, fintechs and lenders across the entire spectrum – small, medium and large, are further exploring and adopting AI-powered solutions to unlock growth and improve operational efficiencies. With increasing competition and a dynamic economy, AI-driven strategies across the entire customer lifecycle are no longer a nice to have, they are a must. Our dedication to delivering on this need for our clients is why we are thrilled to be recognized as a Fintech Breakthrough Award winner for the fifth consecutive year. Experian’s Ascend Intelligence ServicesTM (AIS) platform hosts a suite of analytics solutions and has been named “Best Consumer Lending Product” in the sixth annual FinTech Breakthrough Awards. This awards program is conducted by FinTech Breakthrough, an independent market intelligence organization that recognizes the top companies, technologies and products in the global fintech market today. This is the second consecutive year that AIS has been recognized with a FinTech Breakthrough Award, previously being selected for the “Consumer Lending Innovation Award” in 2021. “Winning another award from FinTech Breakthrough is a fantastic validation of the success and momentum of our Ascend Intelligence Services suite. Now more than ever, the world is in a state of constant change and companies are being reactive, with data scientists spending too much time on manual, repetitive data-wrangling tasks, at a time when they cannot afford to do so,” said Shri Santhanam, Experian’s executive vice president and general manager of Global Analytics and AI. “Companies need to be able to rapidly develop and deploy ML-powered models in an agile way at low cost. We are now able to offer this to more lenders no matter their size.” With AIS, Experian can empower financial services firms to make the best decisions across the customer life cycle with rapid model and strategy build, seamless deployment, optimization and continuous monitoring. The AIS suite is comprised of two key solution models: Ascend Intelligence Services Acquire is a managed services offering that enables financial institutions to increase approval rates and control bad debt by acquiring the right customers and providing the best offers. This is accomplished through a rapid AI/ML model build that will help better quantify the risk of an individual applicant. Next, a mathematically optimized decision strategy is designed to provide a more granular view of the applicant and help make the best decision possible based on the institution’s specific business goals and constraints. The combination of the AI/ML model and optimized decision strategy provides increased predictive power that mitigates risk and allows more automated decisions to be made. The model and strategy are seamlessly deployed to help deliver business value quickly. Ascend Intelligence Services™ Limit enables financial institutions to make the right credit limit decisions at account origination and during account management. Limit uses Experian’s data, predictive risk and balance models and our powerful optimization engine to design the right credit limit strategy that maximizes product usage, while keeping losses low. To learn more about how Ascend Intelligence Services can support your business, please explore our solutions page. Learn more For a list of all award winners selected for the 2022 FinTech Breakthrough Awards, click here.

It is no news that businesses are increasing their focus on advanced analytics and models. Whether looking to increase resources or focus on artificial intelligence (AI) and machine learning (ML), growth is the name of the game. But how do you maximize impact while minimizing risk? And how can you secure expertise and ROI when budgets are strapped?  Does your organization have the knowledge and talent in-house to remain competitive? No matter where you are on the analytics maturity curve, (outlined in detail below), your organization can benefit from making sure your machine learning models solution consists of: Regulatory documentation: Documentation for model and strategy governance is critical, especially as there is more conversation surrounding fair lending and how it relates to machine learning models. How does your organization ensure your models are explainable, well documented and making fair decisions? These are all questions you must be asking of your partners and solutions. Integrated services: For some service providers, “integrated,” is merely a marketing ploy, but it is essential that your solution truly integrates attributes, scores, models and decisions into one another. Not only does this serve as a “checks and balances” system of sorts, but it also is a primary driver for the speed of decisioning, which is crucial in today’s digital-first world. Deep expertise: Models are a major component for your decisioning, but ensuring those models are built and backed by experts is the one-two punch your strategies depend on. Make sure your services are managed by data scientists with extensive experience to take the best approach to solving your business problems. Usability: Does your solution close the loop? To future proof your processes, your solution must analyze the performance of attributes, scores and strategies. On top of that, your solution should make sure the items being built are useable and can be modified when needed. A one-and-done model does not suit the unique needs of your organization, so ensure your solution provides actionable analysis for continual refinement. Does your machine learning model solution check these boxes? Do you want to transform your existing system into a state-of-the-art AI platform? Learn more about how you can take your business challenges head-on by rapidly developing, deploying and monitoring sophisticated models and strategies to more accurately predict risk and achieve better outcomes. Learn more Access infographic   More information: What’s the analytics maturity curve? “Analytics” is the discovery, interpretation and communication of meaningful patterns in data; the connective tissue between data and effective decision-making within an organization. You can be along this journey for different decision points you’re making or product types, said Mark Soffietti, Director of Analytics Consulting at Experian, at our recent AI-driven analytics and strategy optimization webinar. Where you are on this curve often depends on your organization’s use of generic versus custom scores, the systems currently engaged to make those decisions and the sophistication of an organization’s models and/or strategies. Here’s a breakdown of each of the four stages: Descriptive Analytics – Descriptive analytics is the first step of the analytics maturity curve. These analytics answer the question “What is happening?” and typically revolve around some form of reporting. An example would be the information that your organization received 100 applications. Diagnostic Analytics – These analytics move from what happened to, “Why did it happen?” By digging into the 100 applications received, diagnostic analytics answer questions like “Who were we targeting?” and “How did those people come into our online portal/branch?” This information helps organizations be more strategic in their practices. Predictive Analytics – Models come into play at this stage as organizations try to predict what will happen. Based on the data set and an understanding of what the organization is doing, effort is put towards automating information to better solve business problems. Prescriptive Analytics – Optimization is key for prescriptive analytics. At this point in the maturity curve, there are multiple models and/or information that may be competing against one another. Prescriptive analytics will attempt to prescribe what an organization is doing and how it can drive more desired behaviors. For more information and to get personalized recommendations throughout your analytics journey, visit our website.

Chatbots, reduction of manual processes and explainability were all hot topics in a recent discussion between Madhurima Khandelwal, Vice President and Head of DataLabs at American Express®, and Eric Haller, Executive Vice President and head of Experian DataLabs. The importance of AI’s role in innovation in the financial services space was the focus of the recent video interview. In the interview, Khandelwal highlighted some of the latest in what American Express DataLabs is working on to continue to solve complex challenges by building tools driven by AI and Machine Learning: Natural language processing has come a long way in even the last few years. Khandelwal discussed how chat bots and conversational AI can automate the simple to complex to enhance customer experience. Document recognition and processing is another leading-edge innovation that is useful for extracting and analyzing information, which saves staff countless manual hours, Khandelwal said. Fairness and explainability are consistently brought to the forefront especially in financial services as regulators are looking at ways to prevent AI/ML from causing bias for the consumer. Khandelwal showcased how there is extreme rigor in each part of creating their models and how human oversight and training are primary drivers for how they stay on top of this. As for innovation advice, Khandelwal points out that it’s important to be aware that AI and innovation are not always interchangeable, and companies need to think through whether a problem needs to be solved through AI/ML models before charting ahead. Another major key to the equation is the data. In all use cases, the undercurrent of innovation in any form is dependent on the data being used. Learn more about this topic and what Harry Potter has to do with women in data science. Watch the Interview

Shri Santhanam, Executive Vice President and General Manager of Global Analytics and Artificial Intelligence (AI) was recently featured on Lendit’s ‘Fintech One-on-One’ podcast. Shri and podcast creator, Peter Renton, discussed advanced analytics and AI’s role in lending and how Experian is helping lenders during what he calls the ‘digital lending revolution.’ Digital lending revolution “Over the last decade and a half, the notion of digital tools, decisioning, analytics and underwriting has come into play. The COVID-19 pandemic has dramatically accelerated that, and we’re seeing three big trends shake up the financial services industry,” said Shri. A shift in consumer expectations More than ever before, there is a deep focus on the customer experience. Five or six years ago, consumers and businesses were more accepting of waiting several days, sometimes even weeks, for loan approvals and decisions. However, the expectation has dramatically changed. In today’s digital world, consumers expect lending institutions to make quick approvals and real-time decisions. Fintechs being quick to act Fintech lenders have been disrupting the traditional financial services space in ways that positively impacts consumers. They’ve made it easier for borrowers to access credit – particularly those who have been traditional excluded or denied – and are quick to identify, develop and distribute market solutions. An increased adoption of machine learning, advanced analytics and AI Fintechs and financial institutions of all sizes are further exploring using AI-powered solutions to unlock growth and improve operational efficiencies. AI-driven strategies, which were once a ‘nice-to-have,’ have become a necessity. To help organizations reduce the resources and costs associated with building in-house models, Experian has launched Ascend Intelligence Services™, an analytics solution delivered on a modern tech AI platform. Ascend Intelligence Services helps streamline model builds and increases decision automation and approval rates. The future of lending: will all lending be done via AI, and what will it take to get there? According to Shri, lending in AI is inevitable. The biggest challenge the lending industry may face is trust in advanced analytics and AI decisioning to ensure lending is fair and transparent. Can AI-based lending help solve for biases in credit decisioning? We believe so, with the right frameworks and rules in place. Want to learn more? Explore our fintech solutions or click below. Listen to Podcast Learn more about Ascend Intelligence Services

Artificial intelligence is here to stay, and businesses who are adopting the newest AI technology are ahead of the game. From targeting the right prospects to designing effective collections efforts, AI-driven strategies across the entire customer lifecycle are no longer a nice to have - they are a must.  Many organizations are late to the game of AI and/or are spending too much time and money designing and redesigning models and deploying them over weeks and months. By the time these models are deployed, markets may have already shifted again, forcing strategy teams to go back to the drawing board. And if these models and strategies are not being continuously monitored, they can become less effective over time and lead to missed opportunities and lost revenue. By implementing artificial intelligence in predictive modeling and strategy optimization, financial institutions and lenders can design and deploy their decisioning strategies faster than ever before and make incremental changes on the fly to adapt to evolving market trends.  While most organizations say they want to incorporate artificial intelligence and machine learning into their business strategy, many do not know where to start. Targeting, portfolio management, and collections are some of the top use cases for AI/ML strategy initiatives.  Targeting  One way businesses are using AI-driven modeling is for targeting the audiences that will most likely meet their credit criteria and respond to their offers. Financial institutions need to have the right data to inform a decisioning strategy that recognizes credit criteria, can respond immediately when prospects meet that criteria and can be adjusted quickly when those factors change. AI-driven response models and optimized decision strategies perform these functions seamlessly, giving businesses the advantage of targeting the right prospects at the right time.  Credit portfolio management  Risk models optimized with artificial intelligence and machine learning, built on comprehensive data sets, are being used by credit lenders to acquire new revenue and set appropriate balance limits. Strategies built around AI-driven risk models enable businesses to send new offers and cross-sell offers to current customers, while appropriately setting initial credit limits and managing limits over time for increased wallet share and reduced risk.   Collections  AI- and ML-driven analytics models are also optimizing collections strategies to improve recovery rates. Employing AI-powered balance and response models, credit lenders can make smarter collections decisions based on the most predictive and accurate information available.   For lending businesses who are already tight on resources, or those whose IT teams cannot meet the demand of quickly adapting to ever-changing market conditions and decisioning criteria, a managed service for AI-powered models and strategy design might be the best option. Managed service teams work closely with businesses to determine specific use cases, develop models to meet those use cases, deploy models quickly, and monitor models to ensure they keep producing and predicting optimally.  Experian offers Ascend Intelligence Services, the only managed service solution to provide data, analytics, strategy and performance monitoring. Experian’s data scientists provide expert guidance as they collaborate with businesses in developing and deploying models and strategies around targeting, acquisitions, limit-setting, and collections. Once those strategies are deployed, Experian continually monitors model health to ensure scores are still predictive and presents challenger models so credit lenders can always have the most accurate decisioning models for their business. Ascend Intelligence Services provides an online dashboard for easy visibility, documentation for regulatory compliance, and cloud capabilities to deliver scores and decisions in real-time.  Experian’s Ascend Intelligence Services makes getting into the AI game easy. Start realizing the power of data and AI-driven analytics models by using our ROI calculator below: initIframe('611ea3adb1ab9f5149cf694e'); For more information about Ascend Intelligence Services, visit our webpage or join our upcoming webinar on October 21, 2021.  Learn more Register for webinar

The tax gap—the difference between what taxpayers should pay and what they actually pay on time—can have a substantial impact on states’ budgets. Tax agencies and other state departments are responsible for helping states manage their budgets by minimizing expected revenue shortfalls. Underreported income is a significant budget complication that continues to frustrate even the most effective tax agencies, until the right tools are brought into play.   The Problem Underreporting is a large, complex issue for agencies. The IRS currently estimates the annual tax gap at $441 billion. There are multiple factors that comprise that total, but the most prevalent is underreporting, which represents 80% of the total tax gap. Of that, 54% is due to underreporting of individual income tax. In addition to being the largest contributor to the tax gap, underreporting is also extremely challenging to identify out of the millions of returns being filed. With 85% of taxes owed correctly reported and paid, finding underreporting can be like trying to locate a needle in the proverbial haystack. Making this even more challenging is the limited resources available for auditing returns, which makes efficiency key. The Solution Data, combined with artificial intelligence (AI) equals efficient detection. The problem with trying to detect which returns are most likely to have underreported income is similar to many other challenges Experian has solved with AI. Partnerships between Experian and state agencies combine what we know about consumers with what their agency knows about their population. We can take the data and use AI to separate the signal from the noise, finding opportunities to recoup lost revenue. Read our case study on how Experian was able to help an agency identify instances of underreporting, detecting an estimated $80 million annual lost revenue from underreported income. Download case study Contact us