4 strategies to change your approach to fraud detection

Financial institutions are doing business today in a high-risk world. The numbers are more sobering than ever before:

• Fraud threats are evolving rapidly. According to the 2026 Anti-Fraud Technology Benchmarking Report, only 7% of organizations say they are more than moderately prepared to detect and prevent AI-powered fraud. The same report, which draws on global survey insights from more than 700 anti-fraud professionals, found that deep-fake social engineering, consumer scams and generative AI document fraud are among the fastest-growing fraud threats.

• Financial institutions are turning to analytics and AI to strengthen fraud strategies. One in four organizations (25%) now uses AI and machine learning in anti-fraud analytics, and another 28% expect to adopt these technologies within the next two years, according to the 2026 report.

• Technology investment remains a priority despite budget constraints. While 55% of organizations surveyed expect anti-fraud technology budgets to increase, 84% still report budget and financial restrictions as barriers to implementing new anti-fraud tools.
  

Fine-tune your fraud detection strategy

“Fraud doesn’t go away, it’s always changing … and fraud executives must continually invest in anti-fraud technology that goes beyond a single-point solution,” says Thomas French, Advisory Industry Consultant for fraud at SAS. “A business case just won’t deliver a strong enough ROI to warrant the outlay. They have to look deeper to consider (and account for) the impact of fraud on the consumer.”

In their efforts to improve the customer experience while maintaining a robust fraud detection strategy, organizations must use and manage multiple sources of data (both structured and unstructured). Effective anti-fraud analytics initiatives combine internal and external data sources, including structured and unstructured data, public records, law enforcement or government watchlists, social media, third-party data and information from connected devices.

The good news is that advances in fraud prevention, detection and AI-driven analytics technologies give financial institutions more accurate and efficient solutions than ever for uncovering the risk of fraud and financial crimes.

Here are four ways to improve your organization’s risk posture.

1.    Add AI and machine learning to improve fraud detection accuracy and efficiency

It’s proven that machine learning helps organizations detect more fraud – faster and earlier – as it identifies patterns and adapts to evolving fraud and emerging threats. A form of artificial intelligence (AI), machine learning is powerful for improving the accuracy and efficiency of fraud detection and prevention strategies in real-time environments. Applying machine learning to continuously monitor for fraud is a tried-and-true approach to fighting financial crimes.

• Supervised machine learning algorithms can self-learn from target variables within the data, spot red flags (flagging anything that doesn’t fit the norm), then apply this knowledge to new and unseen data.
• Unsupervised machine learning uncovers potentially suspicious types of risks you might not think to look for. It works without being given a target. Instead, it searches for anomalies in the data.

Combined in an ensemble model, machine learning provides a wide breadth of coverage across current risks, as well as new and emerging threats. On top of that, machine learning reduces false positives and helps identify suspicious or previously unknown risks.

As fraudsters increasingly use AI-powered techniques such as deepfake social engineering, synthetic identity fraud and AI-generated document fraud, financial institutions need machine learning models that can adapt to emerging threats while maintaining transparency and accountability. For example, SAS deployed a digital payment model that demonstrated rapid success in real-time fraud detection. It detected 50% of fraud – alerting on just 0.5% of the portfolio, with very few false transactions.

With machine learning, anti-fraud systems can automatically:

• Suggest and update rules for detection and alerts. Machine learning examines large amounts of historical data (and other types of data) to help establish rules and keep them current. 
• Select the most accurate detection models. Applying a combination of machine learning techniques delivers the most accurate detection rates. This approach for detecting and preventing fraud allows newer techniques, like gradient boosting and support vector machines, to enhance proven methods like neural networks.
• Automate processes for investigation. On average, 60% to 70% of an investigator’s time is spent collecting data about a subject to detect fraud. Machine learning can guide systems to automatically search and retrieve data, run database queries and collect information from third-party data providers without human intervention. SAS has helped clients reduce time to case decision by 20% to 30%.
  

2.    Coordinate and operationalize fraud, anti-money laundering and cyber events

Financial institutions are taking advantage of big data analytics to consolidate data across typically siloed functions. Today, it makes sense to bring these functions together for a more holistic view of risk and a more coordinated approach to fraud, financial crime and cyber threats. Much of the data is similar, and regulations are pushing risk identification to real time. There’s also an opportunity to reduce operational costs and enhance efficiency while developing a cross-functional view.

For example, whether reviewing a loan application, making a decision about a payment transaction or uncovering terrorist financing through anti-money laundering (AML) efforts, there are opportunities to learn from every interaction. Achieving real-time agility in a world of faster payments is critical because retail and financial entities must adapt to improve customer experience amid demands for convenience. As fraudsters increasingly use AI-powered techniques and automation to scale attacks, the risk environment intensifies.

• Mobile and online commerce reshape expectations for speedy authentication across all contact channels. Financial institutions need a combination of customer, device and session behavioral analytics to reduce fraud, prevent losses and identify emerging threats earlier.
• More forward-thinking intelligence units are finding common elements – domain names, IP addresses, devices, etc. – that reveal criminal organizations previously undiscovered by siloed functions.
• The demand for real-time funds availability continues to accelerate as instant and faster-payment initiatives gain adoption around the world. Coupled with the growth of fintechs and digital channels, these developments are raising expectations for immediate decisions while compressing the time available to detect and stop fraud. 

Once a luxury, real-time transaction monitoring is now a baseline requirement for all payment types. To counter payment fraud, it’s vital to incorporate not only financial transactions but also authentication, session, location and device event data.

3. Streamline know your customer (KYC) processes

Ongoing regulatory scrutiny and beneficial ownership transparency requirements underscore the need for greater visibility into the real owners and beneficiaries of corporate and legal entities. At the same time, rising concern about synthetic identities, application fraud and AI-enabled fraud schemes is redefining expectations for KYC processes. Both realities increase the need for stronger identity verification, due diligence and customer monitoring.

SAS can help by:

• Fortifying and speeding authentication processes that validate digital devices and in-person applicants.
• Using robotic process automation (RPA) to automate searches and queries of third-party data during enhanced due diligence processes.
• Supporting new data elements, such as ownership percentages and controlling interests.
• Offering investigative interfaces that streamline the ad hoc process of gathering external unstructured information, including numbers, text, images and video.

For document query and retrieval, image recognition capabilities based on natural language processing techniques have shown remarkable results. In one test case, SAS reduced the time to identify, classify and analyze trade documents from 700 hours to a matter of minutes.

In another pilot, we scanned approximately 9,000 SWIFT (Society for Worldwide Interbank Financial Telecommunication) messages to identify potential compliance and financial crime risks. A human would need about five to seven minutes to review each message. During this pilot, we found we could perform image recognition and contextual analysis in less than one second per message.

4.    Improve investigation efficiency with intelligent case management

Much of the initial adoption of AI focuses on automating manual processes to improve the efficiency of fraud and financial crimes investigations. Investigators shouldn’t spend their valuable time on rote tasks that machines can do better. As organizations increasingly adopt automation and AI-assisted investigation capabilities, advanced analytics-driven alert and case management solutions that present a single view of data can automatically:

• Prioritize cases, recommend investigative steps and fast-track straightforward cases.
• Enrich alerts with details about the associated customers, accounts or beneficiaries.
• Intelligently find and pull data for a case from internal databases or third-party data providers.
• Present data in easy-to-understand visualizations on one screen.
• Auto-populate and prepare suspicious activity reports (SARs) for electronic filing if applicable.

About the author

Thomas French, Advisory Industry Consultant, SAS Global Security Intelligence Practice

Thomas French is a strategic leader with more than 30 years of experience in consumer and commercial bank fraud prevention, detection, customer service, claims and recoveries. He works with financial services companies across the globe using SAS to combat bank fraud, AML, cyber threats and internal fraud – and to mitigate operational and reputational risk. 

Explore more resources