Although traditional credit bureau scores provide valuable information about a consumer or SME’s financial situation, they can be limited by being point-in-time insights.

In comparison, trended attributes look at the patterns in credit behaviour over a period of time. By analysing credit usage and repayment patterns over a two-year period, lenders can identify if their customer’s financial circumstances are improving or deteriorating.

These historical trends can be used to more accurately predict whether a customer is likely to repay their loan. Aggregating these data points and combining them as ratios in plug-and-play attributes can improve the accuracy of lending models by up to 20%.

This article explains what trended attributes are and why they are such powerful predictive tools in credit risk assessment. Given the rapid pace of change in the lending environment over the past few years, trended attributes are becoming increasingly important to making profitable and responsible lending decisions.

How do trended attributes simplify analysis?

All of the data points used to develop attributes can be found in standard credit reports. However, in order for lenders to understand the trends hidden in 24 months of trade data, they need to be able to analyse an enormous amount of data.

To illustrate this, let’s consider the following example. Imagine a single consumer with ten trades on file, over a period of two years this means there are at least 1,200 data points to analyse. Now, if you multiply that by a conservative portfolio of 100,000 customers, that means you will need to analyse over 120 million data points. This requires considerable resources and analytical ability, which not all lenders have the capacity for.

Another point to consider is that if this trended data is used to assess creditworthiness in the underwriting process, then it may well be the reason why a customer is declined a loan. In this case, the lender will need to create a set of adverse action reason codes to understand this decision and communicate it to the customer.

Rather than go through all that effort, lenders can access a library of thousands of highly predictive and industry-specific trended attributes from Experian. These can be used to develop new models or used for segmentation overlays. This means you could be enjoying the benefits of trended attributes in only a few weeks.

What insights can trended attributes reveal?

By understanding the financial trajectory of a customer over time, trended attributes can show lenders if their customer’s financial situation is trending up or down. This allows for a much more accurate prediction of future behaviour than only looking at a moment-in-time credit score.

The image below shows how a credit score alone can be misleading, using two example consumers to show why changes in balance over time can reveal a much better understanding of each borrower’s financial situation. Both Jose and Tanya have the same credit score but very different journeys to get there. Which one represents the greatest risk going forward?

The following points illustrate some of the insights that trended attributes can provide:

• Changes in balance – analysing a customer’s balance over time shows if the amount they are borrowing is decreasing, remaining steady or increasing.
• Credit utilisation rate – a customer’s credit utilisation ratio, which represents the amount of credit they have used compared to their maximum credit limit, is a useful metric to understand whether their financial situation is improving.
• Payment patterns – historical repayment behaviour shows if a customer normally makes monthly payments on time and if they have missed any payments. It can also reveal if the frequency of late payments is increasing or decreasing.
• Outstanding debt level – how much a customer’s overall debt position has changed over time is essential to understand if they are accumulating debt or actively paying down their debt.

An example of how these subtle changes in borrower behaviour can have a large impact on risk assessment is monthly repayment trends. If the borrower is shifting from paying down their debt aggressively to only making the minimum repayment, then they could represent a higher-risk lending option. Including this level of granular detail is important in terms of understanding credit risk.

These changes in a potential or existing customer’s repayment rates and debt burden are not reflected in a traditional credit score, yet they are powerful indicators that can significantly improve the accuracy of lending decisions.

What are the benefits of using trended attributes?

By analysing the financial history of potential and existing customers, you can make better lending decisions – both at originations and across the customer lifecycle. This can lead to greater revenue without an increase in risk exposure.

Trended attributes can also improve your ability to provide inclusive financial services by recognising positive credit behaviour.

Here is a breakdown of the benefits that trended attributes can provide at each stage of the lifecycle:

Prospecting

• Identify which potential customers will be the most profitable by understanding their debt burden and capacity to repay.

Originations and onboarding

• Enhance the accuracy of your decisioning models with a comprehensive evaluation of the customers’ historical credit behaviour.
• Expand new customer eligibility without increasing your risk levels.
• Improve customer experience by reducing the time required to assess creditworthiness with automated decision-making.

Customer management 

• Improve the accuracy of customer segmentation by using an attribute overlay to classify customers with greater precision.
• Identify cross-sell and up-sell opportunities with the right products and terms to increase your response rates and reduce customer attrition.

Pre-collections and collections

• Improve your ability to identify and proactively manage financially stressed customers.
• Increase collections predictability and effectiveness by prioritising customers with the capacity to pay.

Are you interested in using trended attributes?

If your business is interested in taking advantage of trended attributes, then contact us today. We can help you identify the most predictive trended attributes for your type of lending and industry. You can benefit from our decades of experience developing and integrating trended attributes across the consumer credit lifecycle.

Experian has been creating best-in-class attributes since 1976, and we have developed thousands of attributes since then. Our attributes use both local and global datasets to summarise consumer and SME credit behaviour in granular detail. You can use our attributes to support a wide variety of modelling and analytical opportunities that enable better decisioning and segmentation.

For more information about our attributes, speak to your local Experian representative or download our Precision Decisions: Unlocking the value of attributes PDF guide.

The post How trended attributes improve credit risk assessment appeared first on Experian Academy.

Credit attributes have existed for centuries. In days gone by, lenders would make credit decisions based on simple attributes such as employment and income. Although the technology involved with lending has radically changed, with powerful computers and Machine Learning (ML), the theory behind attributes remains the same.

In their simplest form, attributes represent a description of the relationship between different data points that can be used to assess credit risk. Each individual data point provides a limited amount of information on credit behaviour but not the full story – for that bigger picture – they need to be aggregated and combined.

Today, attributes are highly complex mathematical descriptions that combine key data points as ratios over time. These attributes can be used in the development of ML-powered credit risk models to improve the precision of lending decisions. They can also be used without the need for new models to improve score overlays, customer segmentation and marketing pre-screening criteria.

This article answers key questions about credit attributes in a simple and understandable way. Although the details of attribute engineering are extremely technical, our aim is to make the concepts behind them readily accessible across all business units.

What are credit attributes?

Credit bureau attributes represent the relationship between data points that are used to describe the financial characteristics of a borrower. They provide greater insight into credit behaviour than a standard credit score. How? By aggregating and combining individual data points, like credit utilisation and balances, into time-based ratios, such as a debt-to-income ratio over 24 months. Attributes can be used for new model development and as overlays to improve customer segmentation, scores, cut-offs and policy rules.

How do credit attributes improve the accuracy of lending decisions?

Credit attributes enhance the accuracy of lending decisions by providing a more comprehensive understanding of a borrower’s financial situation. This goes beyond a basic credit score as it includes factors like financial stability over time and debt management history to paint a more detailed overall picture.

Credit attributes feed into the credit risk models that assess the likelihood of a borrower repaying a loan or defaulting. By identifying and using the attributes that have the biggest impact on predictability, these models can become significantly more accurate.

Can credit attributes be used without developing new credit risk models?

Yes, attributes can be extremely useful to lenders without the need to develop entirely new models. Attributes can be used as a model overlay to improve segmentation precision – classifying borrowers into different risk categories – which allows lenders to tailor interest rates, credit limits and many other actions for each segment.

Using attributes in this way means lenders can take advantage of attributes without needing a complete model rebuild. Delivering faster, more cost-effective results that can provide meaningful improvements to predictability and thus profitability.

What are trended attributes?

Trended attributes analyse a borrower’s behaviour over a given time period to provide a dynamic view of their financial situation. They track key data points, such as loan balances and repayment amounts, to reveal trends that would not otherwise be apparent. These trends give lenders a more nuanced view than a fixed-time snapshot.

When trended attributes are incorporated into a credit scoring model, they improve the accuracy of the assessment by showing the borrower’s financial trajectory. Historical payment trends, such as credit utilisation ratio (credit usage vs. credit availability), provide a better overview of a borrower’s financial situation by identifying if their payment capacity is improving or deteriorating.

How are credit attributes created?

Attributes are created by analysing, aggregating and combining credit data points to identify hidden relationships or patterns in credit behaviour. Each attribute is carefully derived from a huge amount of raw data due to its ability to impact the predictability of the final risk model.

Depending on the size and resources available to the financial institute, they may develop their attributes in-house or source them from credit bureaus. In many cases, lenders work closely with experts from bureaus to identify the most relevant, reliable and predictive attributes for their specific type of lending and market.

Why is it challenging to identify the best attributes?

Just because an attribute exists does not mean that it will improve the accuracy of a credit risk model. In fact, using too many attributes can have the opposite effect and reduce the accuracy of a model. The key is the relevance and the impact on predictiveness of the attribute. Identifying the most relevant attributes for a model is a highly specialised task.

Additional challenges in attribute selection include:

• Data availability – does the lender have access to the necessary raw data?
• Data quality – the accuracy and reliability of the data used to develop attributes is critical to their success, bias or inaccuracies lead to flawed attributes.
• Data aggregation – individual data points can easily amount to hundreds of millions across a portfolio, so aggregation is critical to attribute development.

Download our attribute PDF - Precision Decisions: Unlocking the value of attributes

Download

Does Machine Learning (ML) enhance credit attribute accuracy?

Yes, ML can play a significant role in enhancing credit attribute development by revealing non-linear correlations between data points. ML algorithms can identify complex relationships between multiple data points that may have otherwise been missed.

This can result in attributes that have a stronger predictive power. ML can also be used to create new model features by combining multiple attributes.

How to choose the best attributes for a credit risk model?

Attribute selection depends on the type of lending, the stage of the customer lifecycle and the sector. Experian has a library of thousands of attributes – including a core subset of the most widely used attributes and additional subsets for different industries.

The best attributes to use are those that have the greatest impact on the predictive accuracy of a risk model. Assessing the impact of each attribute and then assigning it a weight within the final model is a complex process.

Do credit attributes need to change over time?

Yes, credit attributes absolutely need to change and evolve over time to retain high levels of predictive accuracy in credit risk assessment. This is due to the constantly changing macroeconomic environment and the resulting shifts in borrower behaviour.

The last few years have seen considerable changes in many consumers’ financial situations due to elevated inflation and interest rates. For younger borrowers, this represents their first cycle of raised interest rates, so attributes that were previously highly predictive may need to be updated to remain relevant.

Trended attributes – that can include data points over a two-year period – are particularly important in light of the rapid changes in interest rates that many regions across the world are experiencing at the moment.

How do attributes contribute to automated credit decisioning?

Attributes play a crucial role in optimising the automation of credit decisions. The right attributes can significantly improve the accuracy and reliability of the models that power lending software. The end result is that businesses can trust that their automated credit assessments are consistent, inclusive and responsible.

Download our attribute PDF - Precision Decisions: Unlocking the value of attributes

Download

Are you interested in using the latest attributes in your decision engine?

If you’d like to boost the accuracy of your credit decisions with the latest and most predictive attributes, then speak to your local Experian representative today. You can benefit from our many decades of experience developing and integrating attributes for use across the consumer credit lifecycle. Using our attributes can deliver as much as a 20% increase in the Gini coefficient predictiveness of a model.

For more information about Experian’s attributes, download our Precision Decisions: Unlocking the value of attributes PDF guide.

The post Attributes: essential tools in credit underwriting appeared first on Experian Academy.

One of the most exciting Generative AI (GenAI) use cases for financial services and telcos is the generation of synthetic data. This data augmentation technology can help businesses improve the predictive accuracy of the models they use to assess credit risk and detect fraud.

Although synthetic data has existed in various forms for some time, the latest advancements in GenAI, specifically Conditional Tabular Generative Adversarial Networks (CTGANs), mean that synthetic data is now a viable option to enhance unbalanced training datasets and precisely simulate hypothetical scenarios.

Generating synthetic datasets has another significant benefit – it allows businesses to share data freely between different parts of their organisation and across borders. This sidestep of regulatory and compliance hurdles is possible because synthetic data is fully anonymised and thus contains no sensitive PII data.

Experian’s recent AI research shows that a lack of data is many businesses’ biggest data-related challenge. Synthetic data generation is an effective way to overcome this problem. This Q&A article answers all your data augmentation questions and provides some real-world examples of how synthetic data is helping businesses improve profitability.

What is data quality?

Data quality essentially means how well a dataset fits its intended use. Good quality data is sufficiently accurate and complete to provide a valid description of what it represents. This means it must be reliable and relevant for its purpose.

What is data augmentation?

Data augmentation involves the creation of synthetic data that accurately represents the statistical distribution of the original real-world data. This new data is then used to improve the predictive accuracy of any model, whether traditional or ML models. The new data enriches the dataset by providing a more balanced and diverse set of records that creates a better dataset resolution and helps prevent overfitting the model.

What is synthetic data?

Synthetic data is artificial data, generated via algorithms that produce new data that retains a statistically accurate representation of the original data. This means that synthetic data can be used to supplement imbalanced or insufficient datasets to improve the predictive accuracy of a model.

What is the best way to create synthetic data?

Various methods are used to create synthetic data. The most effective deep learning technique is a Conditional Tabular Generative Adversarial Network (CTGAN). This method delivers the most complex distribution of data and can include multiple data types in each model. Simple versions, such as Gaussian Copula or Variational Auto Encoders, may also be an alternative.

What are the benefits of using synthetic data?

The main benefit of synthetic data is that it allows businesses to overcome data scarcity issues by creating additional data to improve the accuracy of their credit risk and fraud models. Another major benefit is that it allows businesses to create the data they need to simulate hypothetical future scenarios.

It can also reduce the complexity involved in sharing sensitive data. Furthermore, synthetic data helps simplify GDPR compliance since there is no need to retain the original data once the synthetic data is created.

How can synthetic data improve the predictive accuracy of models?

Data scarcity is often a challenge when developing new models. Synthetic data can help businesses overcome this difficulty by creating more diverse datasets with the ideal balance of data points or creating new ones that help generalise the models and reduce their potential biases. For example, by creating additional fraud data when the real-world training data lacks sufficient data points to develop a robust model. This additional data creates a more balanced training dataset that results in greater predictive accuracy.

How can synthetic data be used to simulate hypothetical scenarios?

Synthetic data can be used to model hypothetical economic situations, such as periods of elevated inflation or a recession. Understanding how a portfolio will react under these extreme conditions can help businesses identify any potential risks and take steps to mitigate them in advance.

Another area where synthetic data can be highly valuable is when entering new markets. In this situation, businesses may lack sufficient historically relevant data to develop accurate credit risk models. Synthetic data can be used to emulate potential credit behaviour in a new market to improve the predictive accuracy of credit decisions.

How can synthetic data help overcome compliance issues around data sharing?

Synthetic data is truly anonymised, which means that any sensitive PII data cannot be inferred from it. As a result, it can be freely shared between business units and across borders as it complies with current privacy regulations around the world. As data-sharing regulations tighten, synthetic data offers a simple and effective way to safely share data without risk.

How does a CTGAN model create synthetic data?

In the case of CTGANs, it uses two neural networks that iteratively learn from each other to produce synthetic data that is indistinguishable from the training dataset. To achieve this, one of the neural networks (the generator) produces new data, while the other neural network (the discriminator) classifies the data as either real or fake.

The generator then uses this feedback to improve the next round of outputs. Over time the quality of the synthetic data improves until the discriminator is unable to determine if it is from the original dataset or is newly created.

How can synthetic data address bias?

Creating synthetic data allows you to selectively correct imbalances that represent bias in your data. In other words, you can generate data for a specific demographic or population that is underrepresented. This means you can create a training dataset that more accurately represents a population and directly address one of the main causes of bias.

What is the secret to creating high-quality synthetic data?

For synthetic data to statistically reflect real-world data as closely as possible, it needs a suitably representative training dataset. The quality of synthetic data is heavily dependent on the quality of this original real-world dataset. Equally important is selecting the right type of data generation model, for example CTGANs. Experian’s extensive global datasets provide an ideal training dataset for a wide variety of best-in-class synthetic data.

Are you interested in using synthetic data in your models?

Experian is uniquely positioned to help your business produce synthetic data via our comprehensive bureau datasets. Once the data imbalance within your model is identified, we can produce the data needed to correct this imbalance. The results of adding synthetic data to a model can be considerable, in some cases as much as a 20-point improvement in the Gini coefficient.

If you would like to know more about how synthetic data can help improve your analytical process, then please contact me via the form below.

The post Data augmentation with synthetic data appeared first on Experian Academy.

According to the IDC MarketScape, key fraud prevention capabilities include AI and Machine Learning (ML), along with the increased computing power that is available via cloud-based solutions.

Why are these two capabilities highlighted as being the most important for fast and effective fraud prevention? The simple answer is that they act as enablers. Cloud allows for easy access to vast amounts of information, with additional compute power on demand. This processing capacity and large datasets are critical to the development of ML-based fraud risk models.

However, ML powers more than just risk models. It is the analytical backbone behind a wide variety of specialised fraud prevention solutions. These range from biometric authentication, behavioural analysis, device fingerprinting, document verification and more.

As a cloud-based fraud platform, Experian’s CrossCore uses ML within its individual fraud solutions but also, crucially, as a means to integrate multiple different solution outputs into a single recommendation. It is this intelligent user journey orchestration that we believe makes CrossCore one of the top fraud platforms in the world.

Highlights from the IDC MarketScape report

The IDC MarketScape: Worldwide Enterprise Fraud Solutions 2024 Vendor Assessment (doc #US51939124, March 2024) provide analysis and insight that help global business executives make fact-based decisions about their technology partners.

The report includes a detailed analysis of fraud solution vendors’ capabilities and strategies, along with current and future market success factors.

IDC MarketScape vendor analysis model is designed to provide an overview of the competitive fitness of ICT suppliers in a given market. The research methodology utilizes a rigorous scoring methodology based on both qualitative and quantitative criteria that results in a single graphical illustration of each vendor’s position within a given market. The Capabilities score measures vendor product, go-to-market and business execution in the short-term. The Strategy score measures alignment of vendor strategies with customer requirements in a 3-5-year timeframe. Vendor market share is represented by the size of the icons

The IDC MarketScape report noted, “In addition to evaluating the transactional data for potential fraud, Experian’s CrossCore solution includes identity-authentication tools. The solution uses identity data, device intelligence, email and phone intelligence, alternative identity data, biometrics, behavioural biometrics, one-time passwords, and document verification to confirm identities and aid with identity protection, including synthetic identity protection. Experian utilizes multiple data partnerships in its fraud solution, which often can help provide a more comprehensive understanding of fraud risks and exposures.”

How does ML-powered fraud orchestration work?

Orchestrating multiple fraud solutions without making the onboarding journey too complicated is a challenge for many organisations. Different risk signals need to be consolidated into a single assessment to reduce friction and provide an automatic overall decision.

This is why Experian developed CrossCore®, an integrated digital identity and fraud platform that combines multiple fraud solutions in a single cloud-based decision engine. CrossCore allows you to seamlessly connect your own fraud solutions with Experian’s, or other third-party providers’ solutions.

In addition, you can customise decisioning workflows for each customer depending on their risk level. The result is that low-risk customers have a streamlined journey, while high-risk customers must complete further authentication steps. This plug-and-play platform can help you future-proof your account opening process by adding new capabilities as they are developed.

Download an excerpt of the IDC MarketScape report

For more information on the IDC MarketScape: Worldwide Enterprise Fraud Solutions 2024 Vendor Assessment, you can download an excerpt from the report.

If you would like to know more about CrossCore®, contact Experian today and speak to a local representative. Our expert consultants can help you identify where your fraud weak points are and advise you on the most effective fraud prevention solution for your business.

The post Experian is a Leader in the IDC MarketScape for Enterprise Fraud Solutions appeared first on Experian Academy.

The arrival of publicly accessible Generative AI (GenAI) represents a groundbreaking leap in technology. Some analysts suggest the impact could be as significant as previous world-changing breakthroughs, such as electricity and the internet. Although this may seem unlikely, one thing is certain – GenAI holds enormous potential.

Within the world of credit risk assessment and fraud prevention, there is a wide range of possible GenAI applications. But to fully take advantage of this potential requires careful consideration and selection of which use cases can provide the highest ROI.

At Experian, game-changing technology is our lifeblood and our large teams of data scientists have been working with GenAI since its inception. This guide offers a window into our data labs to see which GenAI use cases our specialists are excited about and how they can help optimise our client’s core business processes.

Our intention is to highlight the most valuable GenAI use cases that your business can implement to enhance the accuracy of your credit risk and fraud decision-making.

What’s included in our GenAI use case guide?

To give you a comprehensive look at how this exciting technology can be used, we’ve broken our report into the following sections:

1. GenAI vs traditional AI

Differentiating between the capabilities and limitations of traditional AI versus GenAI is an important starting point to get the most value from GenAI. When used in conjunction, these technologies can provide significant improvements in the time required to develop and monitor models, along with enhancing their predictive accuracy.

2. Where can GenAI provide the most value?

With so many different use cases, it is vital to have a thorough understanding of where GenAI and Large Language Models (LLMs) outperform previous algorithms. This knowledge is key to selecting where GenAI fits within an existing technology stack.

3. Business Information (BI) data extraction

Find out how Experian is using GenAI to accelerate and automate the process of analysing and preparing unstructured BI data. This section explores the capability of LLMs to extract, summarise and categorise data points from large BI documents to achieve material gains in the accuracy of business credit assessment models.

4. Model monitoring

Diagnosing and rectifying model drift with a GenAI assistant can greatly reduce the resources required to keep models operating at peak efficiency. Discover how Experian has integrated GenAI into our Model Monitoring Toolbox (MMT) to simplify this process and make model diagnostics accessible to a wider audience within your business.

5. Synthetic data

According to Experian’s recent AI research, a lack of data to assess the creditworthiness of consumer and business customers is the biggest data-related challenge for many organisations. Learn how Experian is combining our comprehensive global datasets with GenAI to produce the highest-quality synthetic data – providing as much as a 20-point improvement in the Gini coefficient of decisioning models.

6. Future Applications of Gen AI

Take a look into what lies ahead on the GenAI use case trajectory. Our data scientists suggest three exciting possibilities of how GenAI can revolutionise credit risk assessment in the months and years to come.

Contact Experian to fast-track your GenAI adoption

As a global leader in data, analytics and technology, Experian is actively exploring over 40 different use cases for GenAI. Our large multinational teams of data scientists have decades of experience working with AI/ML and have successfully developed and implemented thousands of models for businesses across the globe.

This solid foundation of expertise is a critical factor when exploring the potential that GenAI offers. It gives us an in-depth understanding of the benefits, as well as the challenges, involved with implementing this new technology.

At the core of our purpose is the use of technology to drive automation, efficiency and profitability in a safe and responsible way. Our approach to AI ensures compliance with regulatory requirements for accounting, auditing and model explainability.

We encourage you to reach out to us, to discuss how your business can take advantage of this exciting technology. The GenAI use cases we have highlighted in our guide are only the beginning, and in the coming months, we will continue to update you on the ongoing evolution of this critical technology.

Our team of specialised consultants is ready to help you through each stage of identifying and developing the right GenAI applications for your business. Contact us today to speak to a local representative and fast-track your automation and efficiency with GenAI.

The post Top generative AI use cases in Financial Services appeared first on Experian Academy.

In today’s world of heightened geopolitical and fraud threats, conducting thorough PEPs and sanctions checks is not just a regulatory requirement but a proactive step to maintain trust and ensure the integrity of your business within the global financial ecosystem. These screening processes serve as a vital safeguard against illicit activities.

By identifying and monitoring PEPs, you can mitigate the risk of being unknowingly involved in corruption, money laundering or other fraudulent activities. Sanctions screening can help prevent any association with organisations or individuals that are under sanctions – to protect your business, reduce legal and reputational risks, and avoid potentially large fines.

This article explains the key terms involved with PEPs and sanctions screening in a Q&A format. For a deep dive into this topic, please read our comprehensive PEPs and sanctions challenges guide, with expert advice from an Experian specialist.

Understanding PEPs and sanctions: key questions

What are PEPs?

Politically Exposed Persons (PEPs) are individuals who have been entrusted with prominent public positions or have held positions in the recent past, exposing them to potential financial corruption. These individuals could range from heads of state, such as prime ministers and presidents, to city mayors, religious leaders, or local government officials.

What are the risks of conducting business with a PEP?

PEPs usually have access to resources and political power and, as such, could influence policy or people. This can potentially present a risk to your business. However, it is not prohibited to do business or provide financial services to someone who is a PEP, but greater caution should be taken when dealing with them.

Another concern is that they are more at risk of impersonation. As public individuals, a lot of their personal information is available online – which makes them a prime candidate for impersonation. This risk has been exacerbated by the recent advances in deepfake technology. Therefore, if an individual flags as a PEP, you may wish to carry out additional due diligence checks to ensure you are dealing with the genuine individual.

Is it only the PEP that represents a risk?

No. Relatives, such as wives, husbands, children, and wider family members, as well as close associates, such as business associates and employees of a PEP, could present a risk to your organisation. AML regulations state that these individuals should also be checked and monitored to the same level as the PEP.

What are sanctions?

Financial sanctions are punitive or restrictive measures designed to maintain or restore international security. These measures are typically deployed in response to activities deemed unacceptable, such as violations of international law, human rights abuses, or threats to global peace. Sanctions can take various forms, including trade restrictions, asset freezes, travel bans, and financial penalties.

Who issues sanctions?

Governments and international organisations such as the United Nations, the European Union and the Organisation for Security and Cooperation in Europe (OSCE).

What are sanctions lists?

Sanctions lists are a directory that contains all the individuals and entities (organisations, aircraft, banks and vessels) that are subject to restrictive measures. The lists also contain additional information about the sanction. For example, if the order prohibits businesses from providing financial services to the person or organisation.

How do PEPs and sanctions screening relate to Anti-Money Laundering (AML) processes?

Sanctions screening is an integral part of the AML process, which is designed to detect and prevent the disguising of criminally obtained money, typically through transfers involving foreign banks or legitimate businesses.

It helps organisations comply with regulatory requirements, mitigate risks, and contribute to global efforts to combat money laundering and terrorist financing. Sanctions screening focuses on identifying and thus preventing any transactions with individuals, organisations, or countries that are subject to sanctions.

How do PEPs and sanctions screening relate to Know Your Customer (KYC) and Due Diligence (DD) checks?

Sanctions and PEPs screening is a critical component of effective KYC and DD to provide financial institutions with a robust risk management framework, ensuring that they are well-informed about their customers and business partners.

What are the potential consequences for businesses that fail to comply with PEPs and sanctions screening regulations?

Businesses that fail to comply with sanctions regulations can face severe consequences, both legal, financial and reputational. Regulatory bodies impose hefty fines for non-compliance, and these fines can be substantial, depending on the severity of the violation. Additionally, businesses may be subject to legal action, or exclusion from certain markets.

The reputational damage can be equally, if not more, damaging. Non-compliance with sanctions can lead to a loss of trust among customers, partners, and investors. Financial institutions may find their credibility eroded, impacting their ability to attract and retain clients.

Are you looking to conduct PEPs and sanctions screening?

Experian can help you navigate this complex and constantly evolving process with our simple and reliable solution called CrossCore Watchlist Service. It provides real-time screening across a comprehensive global database of PEPs and sanctions lists with a simple integration into your onboarding system.

For more information about CrossCore Watchlist Service, simply fill out the form below, and we will send you the brochure with a detailed breakdown of the benefits the solution provides and how it works.

The post Understanding PEPs and sanctions screening: an overview appeared first on Experian Academy.

Sanctions and Politically Exposed Persons (PEPs) watchlists are constantly changing as the geopolitical environment evolves. The challenges involved with screening potential clients and business partners against these lists are considerable – especially since there are thousands of lists worldwide.

At the same time, the consequences of unknowingly conducting business with a sanctioned individual or organisation are severe. These can include substantial fines issued by regulatory bodies, exclusion from trading in certain markets, and significant damage to your reputation and credibility.

The intention of this guide is to help you navigate this challenging process by highlighting key issues involved with PEPs and sanctions screening and how they can be avoided. The insights are provided by one of Experian’s top experts in this field: Sarah McCallum.

For a summary of this topic, we invite you to watch the interview below.

What are the biggest challenges when conducting sanctions and PEPs screening?

The three main challenges involved with the sanctions and PEPs screening process are as follows:

• Ensuring that the checks you carry out are sufficiently robust to comply with the regulators, both at the point of application and then throughout the customer lifecycle
• Making sure that you are keeping up to date with the latest versions of the sanctions and PEPs lists
• Maintaining a consolidated view of all the relevant lists

How can you ensure the sanctions and PEPs data you are checking is the most up-to-date information?

This is particularly challenging for organisations that compile the lists and conduct these checks in-house, as the only way to verify that the information they are using is up to date is to manually cross-reference each data source on a daily basis.

However, with the help of third-party service providers – that consolidate all the relevant sanctions and PEPs lists – it is much easier to ensure that the lists you are using to conduct checks are accurate and constantly kept up to date with the most recent changes.

What is the best way to deal with name variations and data inaccuracies?

The most effective way to avoid these issues is to use a technique known as fuzzy matching. This can be applied to every check to ensure that variations such as an inverted forename and surname, or people that use their middle name as their first name, are flagged and the correct person is identified.

By using this method, it is also possible to check for common spelling variations. For example, Sarah is often spelt as Sara, and there are many other subtle variations that are often missed with direct matching, such as Jayne/Jane and Mohammed/Mohammad.

How can PEPs and sanctions screening be incorporated into identity and fraud checks?

With the right software solutions, it is simple to carry out PEPs and sanctions checks as part of your identity and fraud screening process during onboarding. These checks can be integrated with other identity checks – such as document verification – to ensure that you have a comprehensive and holistic view of the individual.

Are you looking to improve your PEPs and sanction screening process?

Experian can help you navigate this complex and constantly evolving process with our simple and reliable solution called CrossCore Watchlist Service. It provides real-time screening across a comprehensive global database of PEPs and sanctions lists with a simple integration into your onboarding system.

CrossCore allows you to connect and orchestrate multiple fraud services within a single platform, and with the addition of our Watchlist Service, you can proactively manage risk within a unified fraud-and-anti-money-laundering (FRAML) framework.

For more information about CrossCore Watchlist Service, simply fill out the form below, and we will send you the brochure with a detailed breakdown of the benefits the solution provides and how it works.

The post PEPs and sanctions challenges: how to overcome them appeared first on Experian Academy.

Professional cybercriminal fraud syndicates are growing in size and complexity, with increasing levels of collaboration. This unfortunate reality was highlighted in the European Union Agency for Cybersecurity’s most recent Threat Landscape Report. The impact of these criminal alliances is evident in the alarming rise in fraud losses over the last year.

Experian’s latest fraud research indicates that nearly three-quarters (73%) of the senior fraud leaders surveyed have seen an increase in fraud losses during the previous financial year. A similar number of leaders (71%) state that they are struggling to keep up with the rapidly evolving fraud threat. These alarming figures indicate that the threat of organised fraud is becoming more severe.

One of the most effective ways to counter this growing threat of transnational professional fraud rings is for businesses to join forces for mutual protection. By joining a fraud consortium and sharing real-time fraud data, businesses can move onto the front foot and proactively defend themselves against attacks. This article explores the benefits of fraud consortia and why they have become essential tools in safeguarding businesses and their customers.

For a brief overview of the benefits of joining a fraud consortium, we invite you to watch the interview below. It features Neel Kamal, the Head of Identity and Fraud for Experian India. He manages a highly effective consortium and discusses how they can elevate fraud prevention for their members.

What is a fraud consortium?

A fraud consortium is a network of organisations that share information relating to fraud attacks, fraud detection technology and fraud prevention strategies to improve their ability to combat fraud. By combining their resources and data, the consortium members can fight fraud far more effectively than they can as individual organisations.

This real-time sharing of anonymised fraud data allows all of the members to proactively update their defences whenever one of them is attacked. This collective approach to fighting fraud can help to significantly improve fraud detection and reduce fraud losses.

Experian operates a number of fraud consortia around the world, with a FinTech-focussed consortium recently launched in the U.S. When new members join one of these consortia, they see, on average, a 20% uplift in their fraud detection accuracy. In addition to this improvement, many participants also report a pronounced reduction in their fraud attack rates, as organised cyber criminals choose to avoid targeting businesses within the consortium.

Fraud consortia overview across EMEA and APAC

For a better understanding of the current state of fraud, Experian recently commissioned Forrester Consulting to survey over 300 fraud decision-makers across the EMEA and APAC regions. The results of this study indicate that only a third of respondents (33%) are currently members of a fraud consortium.

However, half of the respondents (50%) stated that they plan to invest in joining a fraud consortium in the next twelve months. This encouraging trend shows that many fraud leaders recognise the value of collective fraud data sharing and are actively pursuing this goal in an effort to reduce fraud losses.

This will help to address another key finding from the research – that many businesses do not have access to enough data to effectively identify fraud. 70% of the fraud leaders in the survey agree that their organisation lacks quality data to prevent fraud. A clear indication that there is an urgent need for more fraud data sharing between businesses.

What are the benefits of joining a fraud consortium?

For Financial Services and Telco providers to successfully identify and prevent fraud, they require large databases. In most countries, there are only a handful of Telco providers, which means that each organisation usually has a large database. In contrast, there are often dozens of financial institutions, with each organisation having a much smaller database.

This is where a fraud consortium can be particularly effective as they allow FinTechs access to a collective pool of fraud data. For example, Experian India has one of the largest consortia networks within Experian, with over 250 million application records. This highly successful consortium is growing at around 12 million applications per month. As a result, its members are at the cutting edge of fraud trends, and new members can see an immediate reduction in their fraud losses.

Some of the main benefits of being involved in a consortium include the following:

• Sharing of anonymised fraud data between members
• Access to additional expertise from a collective pool of fraud specialists
• Real-time fraud trend identification across the consortium
• Optimisation of fraud detection strategies
• Sharing of regulatory updates and compliance
• Greater influence in negotiations with regulatory authorities and law enforcement
• Sharing of best practices and the adoption of new fraud prevention technology

Is your business interested in joining a fraud consortium?

Experian has a number of active fraud consortia around the globe. Contact us today to speak to a local representative and find out how your business can strengthen its fraud prevention by joining one of our established consortia.

For more information about the latest fraud challenges and solutions, simply fill in the form below, and we will send you a complimentary copy of our latest fraud research: Defeating Fraud: AI as the guardian at the gates of digital business.

The post Fraud consortia: essential tools in the fight against fraud appeared first on Experian Academy.

The fight against fraud is constantly evolving. Experian’s recent fraud research shows that 71% of the fraud leaders in our survey are struggling to keep up with the rapidly evolving fraud threat. But as new technology creates opportunities for fraudsters, so too does it enable better fraud prevention.

This balance between fraud attacks and prevention is highly dynamic, and the only way to stay ahead of fraudsters is to take advantage of the latest fraud detection technology. The demand for new technology is clear, with 73% of businesses in the survey seeing their fraud losses increase in the past 12 months.

So, what are these critical technologies that can help businesses combat fraud more effectively?

Our research indicates that Artificial Intelligence (AI) and Machine Learning (ML) are now pivotal technologies in this fight, and when combined with device data and biometrics, can help swing the balance in businesses’ favour. In this article, we take a detailed look at the top five challenges that are limiting fraud prevention and explore which fraud solutions can fill these gaps.

Essential fraud prevention layers: ML, device data and biometrics

The graphic below shows the key fraud prevention challenges identified in our research with Forrester Consulting.

1^st Challenge – device fingerprinting

According to our research, the biggest challenge limiting respondents’ ability to prevent fraud is a lack of device fingerprinting (56%). Although device data is not a new fraud signal, the incorporation of ML analysis and additional data points means that it has now become an essential tool for effective fraud prevention.

There are three key capabilities associated with device fingerprinting that make it a must-have:

1. Rather than a single point-in-time fraud check, device data can be monitored continuously throughout a user session. This continual assessment allows businesses to flag suspicious devices before the user completes the application or purchase.
2. Unlike active fraud checks, that introduce additional friction into the user journey, device fingerprinting is a completely passive fraud check. This means customer experience is improved while still retaining high levels of fraud detection accuracy.
3. With the rise in synthetic identity fraud, it has become critical to monitor the data trail of each user who interacts with a website.

2^nd Challenge – physical biometrics

The second biggest fraud challenge is a lack of physical biometric identity verification (54%). Despite the remarkable development of deepfakes – created with Generative AI – facial recognition combined with active liveness detection is still the current best practice in terms of identity authentication.

The benefit of this type of authentication is that it improves customer experience by providing a fast and simple way to verify identity against a government-issued ID document. The user can simply take a photograph of their ID and then record a short selfie that includes liveness detection. An added layer of security is provided by active liveness detection, where the user is asked to smile or move their head in a certain way to ensure it is a real person whilst also preventing the use of deepfakes.

Although the recent advances in deepfake technology mean that fake static images are virtually indistinguishable from real ones, they are not yet able to respond in real time. This is why active liveness detection is essential to confirm that the user is who they say they are.

For an overview of the crucial role that physical biometrics plays in a layered fraud prevention strategy, watch the video below. It features one of Experian’s top fraud specialists: Wilnes Goosen.

3^rd Challenge – multiple fraud solutions

Managing multiple types of fraud prevention software and the associated costs is the third biggest challenge limiting businesses’ ability to prevent fraud (52%). As the fraud threat becomes more complex, there is a growing need to use a variety of fraud solutions to stay ahead. Our research shows that 46% of respondents are using three or more fraud solutions, with the majority using a combination of in-house solutions and those provided by external partners.

Integrating these different solutions in a seamless way requires an orchestration solution that can dynamically call up fraud checks based on the risk profile of the user. To address this challenge, Experian developed CrossCore – a fraud orchestration solution that brings multiple fraud solutions together in a single platform.

The advantage of this approach is that it allows you to connect and manage all of your identity and fraud solutions (both internal and third-party) in a simple and efficient way. This reduces the IT complexity involved with deploying multiple fraud solutions, while also combining the output of each fraud check for a more holistic final decision.

4^th Challenge – false positives

The fourth biggest fraud challenge is an inability to align fraud prevention and revenue growth strategies (54%). Central to this challenge is the issue of false positives. According to our research, a staggering 70% of respondents state that false positives cost them more than fraud losses.

To overcome this issue, businesses need to look at the latest technology that allows them to balance effective fraud prevention against high-quality customer experience. Legacy rule-only approaches are no longer sufficiently capable of controlling fraud without introducing large numbers of convoluted rules that ultimately result in high volumes of false declines.

The solution lies with fraud checks that can be continuously and passively monitored, such as device fingerprinting and behavioural biometrics – known collectively as device intelligence. Incorporating these capabilities can significantly improve the detection accuracy of both fraudsters and genuine customers, which means fewer false positives. In addition, they provide the best possible customer experience as they do not interrupt the user journey.

5^th Challenge – referrals

The final fraud challenge is a growing number of referrals, causing increased delays and costs (51%). Large numbers of manual reviews are a symptom of an inefficient fraud prevention strategy. To effectively automate your fraud decisioning process requires a combination of the capabilities discussed above.

By introducing ML-powered fraud solutions that use device and biometric data to near instantly classify users, you can be confident in the accuracy of your fraud detection without relying on manual reviews. The results can be seen in the image below.

Future-proof your fraud prevention with Experian

Experian is on a mission to make the digital world a safer place, and our fraud prevention and orchestration solutions are at the cutting edge of fraud detection technology. As the fraud threat mutates, our fraud solutions continually adapt to help you keep pace and protect your business and customers.

Contact us today to speak to a local representative and find out how to future-proof your fraud prevention process. For a comprehensive overview of the fraud landscape, read our latest fraud research report – simply fill out the form below, and we will send you a complimentary copy.

The post Top 5 fraud prevention challenges and how to overcome them appeared first on Experian Academy.

As fraud becomes increasingly more complex and automated, finding a balance between effective fraud controls and high-quality customer experience is difficult. The one-size-fits-all approach of traditional rule-based fraud detection is inadequate at preventing AI-powered fraud while still providing genuine customers with a fast and simple application or purchase journey.

Of equal importance is the need to reduce the volume of false positives that are often accepted as an inevitable consequence of fraud controls. According to Experian’s latest fraud research, 70% of the fraud leaders we surveyed stated that false positives cost their organisations more than fraud losses.

The solution to both of these challenges is to use behavioural biometrics and device fingerprinting, together referred to as device intelligence. As the ultimate fraud prevention tools, they allow for continuous and passive fraud checks that can identify the most sophisticated fraud attacks while reducing false positives and ensuring the best possible customer experience.

Watch our “Experian Expert Talks” on device intelligence

In the interview below, Siham Laroub discusses why device intelligence is critical to fraud prevention. Siham is a top fraud specialist involved with the development of Experian’s state-of-the-art fraud solution.

How do device fingerprinting and behavioural biometrics work?

Device fingerprinting

This technology is the equivalent of a digital passport for your device. It works by identifying the unique set of attributes associated with each device. These attributes range from hardware specifications to browser configurations and include data points such as the operating system, screen size, time zone, geolocation and IP address.

Although this technology has existed for decades, its value as a fraud signal has improved over time by incorporating Machine Learning (ML) analysis of additional device attributes. Experian’s most recent fraud prevention solution uses over 150 different device data points to calculate a risk score.

Another key element of this technology is that, unlike a cookie, the data that is collected via device fingerprinting is not stored on the user’s device. Instead, it is stored on the merchant or fraud service provider’s server. This means that the user cannot modify or delete it.

Behavioural Biometrics

Just as device fingerprinting creates a unique set of device attributes for each device, behavioural biometrics can be used to create a unique user profile. It does this by collecting and analysing user behaviour, such as mouse movements, keystrokes or touchscreen pressure and many hundreds of other behavioural attributes.

We each have a distinct and subconscious way of interacting with our devices, and this data can be used to create a set of behavioural attributes unique to each user. In addition, this data can be compared to established fraudster or bot behaviour to add another layer of security. User behaviour provides a powerful fraud detection signal, and analysing data points like the time taken to enter your name can reveal whether the user is legitimate or not.

By comparing each user’s behaviour with a large dataset of established good and bad signals, the result is that genuine customers and fraudsters can be accurately identified in close to real time. This means that fraud detection accuracy improves while also reducing the number of false positives.

Any suspicious activity or known fraud signals will instantly trigger an alert that blocks the transaction from occurring or requires additional identity verification checks. Another advantage is that unlike many fraud prevention techniques, behavioural biometrics does not require the collection of any Personally Identifiable Information (PII).

Why is device intelligence the future of fraud prevention?

As the fraud landscape constantly evolves, there are two key aspects to bear in mind. The first is that fraud rings are becoming increasingly organised, and the second is that fraud attacks are becoming more sophisticated with the use of Generative AI. As a result of these developments, single-point-in-time fraud prevention measures are no longer sufficient.

Instead of having a single fraud check that, once passed, gives users complete access to a business’s website, it is now necessary to continuously monitor each user session for fraud signals. This is where device intelligence stands out, as it allows businesses to continuously and passively monitor their users’ devices and behaviour.

The benefit of this approach is that it has zero impact on user experience as it does not involve any additional checks to complete. Moreover, it can be monitored from the first moment a user starts interacting with a website. This is especially effective at identifying fraud attacks that are otherwise difficult to detect – such as synthetic identity fraud and automated bot attacks – as it depends on user behaviour rather than relying on an analysis of their PII data.

Some analysts refer to device intelligence as an “invisible fraud solution”, and it is exactly this capability, along with its unmatched accuracy in detecting fraud, that makes it the future of fraud prevention.

How device intelligence addresses customer experience challenges

Experian’s recent survey of over 300 fraud leaders shows that the top three digital customer experience challenges can be directly addressed by device intelligence. Let’s break down each challenge for a closer look:

Verifying digital customer identity – interpreting how a user inputs their PII data provides a crucial signal for identity verification, without impacting their journey flow. When this is combined with device data, the result is a highly accurate and completely passive method of identity authentication.

Balancing revenue growth with fraud prevention – at the heart of this challenge is the issue of false positives. The strength of analysing device data and user behaviour is that it allows for a more accurate identification of both legitimate customers and fraudsters. This brings fraud losses down while also reducing false positive rates.

Providing a frictionless digital application/purchase journey – device intelligence is the definitive frictionless fraud check as it happens entirely in the background and does not require any action from the user.

Find out more by downloading Experian’s latest fraud research report

For more information about device intelligence contact Experian today and speak to a local fraud specialist. We have a range of cutting-edge fraud solutions and can help you integrate multiple fraud solutions into a single platform.

To get all the insights from our latest fraud research report, simply fill out the form below, and we will send you a complimentary copy.

The post Why device intelligence is essential to combat fraud appeared first on Experian Academy.