Home / Banking Strategies / Detect, protect, perfect: Eight steps to supercharge your fraud detection techniques

Detect, protect, perfect: Eight steps to supercharge your fraud detection techniques


Across industries, financial crimes investigators—even those packing an arsenal of fraud detection techniques—have plenty to keep them awake at night. According to Javelin Strategy & Research’s report, 2017 Identity Fraud: Securing the Connected Life:

  • Identity fraud hit a record high in 2016 with 15.4 million victims in the U.S.
  • From 2015 to 2016, card-not-present fraud rose 40 percent, and account takeover was up 31 percent.
  • As EMV chip cards have curtailed credit card fraud, fraudsters have turned to more online fraud.

No organization wants to make headlines over fraud losses or data breaches, whether it involves monetary or personal information. The reputational hit can sometimes be even more damaging than the direct dollar loss, which is painful enough. The top 10 fraud types alone accounted for $181 billion in losses in 2016.

So how to improve your success and avoid common pitfalls in detecting and investigating fraud? Hint: It’s not all about your fraud detection techniques. It also concerns how you embed those techniques into business practices and keep them tuned over time. These eight action steps will put you on the path to first-rate fraud detection.

1. Connect the dots

Some of the most onerous risks are difficult to detect with isolated transaction monitoring systems. One system might flag a transaction—but without a complete view of an entity’s relationships, the investigator could deem it innocuous.

Imagine the power of a holistic view of connections among accounts and transactions, across channels and products, that spans a network of potentially related customers. By connecting the dots, you could find hidden risk that spreads across multiple systems, falls below rule thresholds, or only reveals itself in broader context.

2. Use hybrid analytics

Relying too heavily (or even exclusively) on a single technique or model type for detecting fraud leads to a common pitfall. As fraudsters grow more sophisticated, it takes a combination of approaches to spot their handiwork.

For example, network analysis finds patterns among linked entities—great for insurance claims fraud and anti-money laundering—but doesn’t detect all varieties of fraud or lend itself to real-time detection. A hybrid approach blends multiple analytic techniques from different disciplines (along with business rules) to provide a far more powerful and accurate fraud detection system.

3. Tap into machine learning

Unlike rules, which fraudsters find easy to test and circumvent, machine learning adapts to changing behaviors in a population through automated model building. With every iteration, the algorithms get smarter and more accurate.

With machine learning, you can encode large numbers of conditions, variables and events into models and detect anomalies that rules and human analysts would miss. Ensembles of different machine learning models and techniques have proven extraordinarily accurate.

4. Bring transparency to ‘black box’ processes

Machine learning models look at so many things in so many ways that, after a model is trained in machine learning, no one can know for certain how it comes up with the outputs: thus the moniker “black box.” Yet investigators need to understand the rationale behind why something rises to their attention. That calls for a “white box” companion that explains and advises. This could be a scorecard, a set of visuals or an auto-generated narrative that gives investigators the needed data and insights to explore the case.

5. Challenge the models

The accuracy of analytical models naturally drifts over time. Good model management calls for two approaches to identify that drift and sustain high model performance:

  • Monitor model inputs, outputs and results so you can see when underlying conditions change and models need upgrading.
  • Periodically create a new variant—a challenger model—and test it by running transactions through it. Then compare the results with the current champion model. If the challenger proves significantly better, it becomes the champion and the improvement cycle starts anew.

6. Make room for prospecting

In a virtual data sandbox, keep looking for new patterns of activity. Test new hypotheses, validate old ones and listen to the possibilities suggested by the data. With unsupervised machine learning, the self-directed algorithm learns the structure of the data, flags anything that doesn’t fit the norm, and then applies this knowledge to new and unseen data. It’s easy to see the value of this fraud detection technique to uncover new and emerging threats.

7. Automate investigators’ work

Investigators shouldn’t spend valuable time on rote tasks that machines can better execute. Use analytics to streamline those processes and boost productivity. For example, an analytics-driven fraud solution can automatically:

  • enrich alerts with detail about the associated customers, accounts or beneficiaries
  • find and pull data for a case from internal databases or third-party data providers
  • examine data masses to help establish fraud detection rules and keep them current
  • present data in easy-to-understand visuals appropriate for the fraud type under review
  • prepare and file suspicious activity reports and other standard investigator outputs
  • prioritize cases, recommend investigative steps and fast-track straightforward cases

An automated and informed system enhances case workflow. Investigator feedback makes the overall system smarter over time.

8. Think system, not just step sequence

Above all, implement fraud detection and investigation as a system: well instrumented, with a continuous feedback loop. Monitor the entire process to track what’s happening, the decisions and actions taken and outcomes. Improvement becomes a journey, a regular cycle of evaluating and training a coherent, connected system. It’s also an eight-step prescription that, among other things, promotes a very good night’s sleep.

Want more Banking Strategies? Sign up for our free newsletter!

Mike Ames leads the Data Science group for the Fraud and Security Intelligence Practice at SAS.

If you enjoyed, this article, check out our recent Executive Report: Fraud and cybersecurity: Staying steps ahead.