How Machine Learning can Reduce False Positives, Increase Fraud Detection
Softjourn

How Machine Learning can Reduce False Positives, Increase Fraud Detection

This subset of artificial intelligence can create unique fraud detection systems for financial institutions that can secure customer information by increasing fraud detection

October 28, 2019 by Softjourn

More than half the respondents to KPMG’s 2019 Global Banking Fraud survey reported that they were only able to recover 25% of fraud losses. This is a clear indication that proactive fraud prevention is key, and banks are investing in a variety of new technologies. One technology that is rising to the forefront is machine learning.

Machine learning is the practice of “teaching” machines to recognize patterns in large amounts of data by providing input and output labels. While the term is often used interchangeably with artificial intelligence, machine learning is actually a subset of this type of data science. Machine learning has already been expressed in many applications and technologies that we are familiar with today, such as website chatbots to provide better customer service and receipt recognition to lessen the amount of time it takes to input information and increase accuracy by removing human error.

This type of technology is already being implemented in the financial industry with great success —but it has not yet been widely adopted due to misinformation and lack of knowledge. Let’s take a closer look at the problem machine learning seeks to solve, and how it can accomplish that task.

The Problem

Technology is both improving the overall quality of our lives and also speeding progress at an increasing pace. Because of these developments, financial institutions can process millions more transactions faster and with greater accuracy than ever before. According to estimates, global payments are expected to approach $3 trillion in the next five years.1 

But this also creates a bigger opportunity for fraudulent transactions. By sneaking in through the thousands of valid transactions processed every fraction of a second, fraudulent activity grows harder and harder for humans to detect. McAfee estimates that cybercrime cost the global economy about $600 billion in 2018.2 The number of institutions experiencing financial fraud, whether successful or not, also continues to increase year over year.

Humans cannot keep pace with the rapid development of technology and must rely on machines to combat the issues that arise with new and changing processes that technology creates. However, many financial institutions still rely on rule-based fraud detection, which are manual systems created by fraud analysts that cannot keep up with the real-time data streams that are increasing at a frequent pace. What's more, these rule-based systems cannot understand correlations or anomalous activity in accounts that could imply fraudulent activity. Using this technology, it currently takes 40+ days for brick-and-mortar financial institutions to detect fraud.3 

This leaves customers wondering and waiting if their accounts have been tampered with, and if their information, much less their money, has been stolen. According to Altexsoft, 20% of customers change banks after experiencing a scam. Financial  institutions risk their business and reputation when they waste hours and money on unnecessary customer interactions when it comes to understanding if a singular transaction was valid or not; multiply that by the thousands of transactions now happening every second and you can easily see how this quickly becomes problematic at many levels.

But with machine learning, banks can combat fraud by using the information they already have. Let’s take a closer look at this type of data science and how it can help prevent financial fraud.

A Possible Solution

Machine learning, closely related to computational statistics, builds a baseline mathematical model from “training data” using the direction of an algorithm. This allows the machine to make predictions without being explicitly programmed to perform a specific task. The more data a machine has to “learn” from, the more accurate it will be. This kind of technology can be used to identify normal consumer spending and differentiate it from activities that might be associated with a fraudulent charge.

Payments are one of the most digitized parts of the financial industry, due to the rise of mobile payments and the increasing need for a better customer experience. Because they are so digitized, payments are vulnerable to digital fraudulent activity. Banks that are trying to retain clients and lure prospects away from competitors want to provide the best experience for their customers. They do this by whittling down the number of verification steps involved in completing a transaction, which lessens the effectiveness of rule-based systems.

Machine learning can fill in the gap because it can not only review existing data to learn about customer spending habits but eventually understand the fluctuating nature of customer spending throughout the year (for example, travel at different times of the year, holiday spending, etc.). Because of this, machine learning can lessen the number of false positives typically identified by rules-based systems that cannot distinguish anomalous but not necessarily fraudulent behavior. One case study from Teradata showed that the implementation of machine learning reduced false positives by 60%, and was expected to rise to 80% as the model continued to learn.4

How It Works

One of the easiest types of fraud to detect and therefore prevent is credit card fraud, which has been exacerbated by the growth in online transactions. Large volumes of data are collected, and because of this, machines can be trained to detect financial fraud. Through pattern recognition, machines can point out irregular types of actions within different customers’ profiles.

Machines are trained using algorithms as a set of instructions on how to group or cluster information in order to best draw patterns and conclusions from the overall dataset. There are many types of algorithms used to “train” machines, but the two most popular are supervised and unsupervised models. 

Machines build models by digesting and labeling information to create a baseline with which to compare new information and thus detect if a new input is anomalous or not.

Supervised Models

A supervised model is the most common form of machine learning across all disciplines. It involves feeding the machine a rich set of labeled or “tagged” inputs; for the financial industry, this data set can be transactions “tagged” to indicate whether it is or is not fraudulent. Machines then digest massive amounts of tagged transaction details so they can create and understand consumer patterns that best reflect legitimate behaviors. The more information used in creating a supervised model, the more accurate the baseline model will be.

Unsupervised Models

Unsupervised models are different from supervised in that the model is constructed from data that is not tagged. This is usually because it is difficult to identify which details will lead to the output desired. Instead, a form of self-learning must be used to reveal patterns in the data that are invisible to other forms of analytics.

These types of models are used to find outliers that were previously unknown, such as new fraudulent activity that has not been seen before. Discrepancies in the data that might indicate fraudulent activity are evaluated at the individual level as well as through sophisticated group comparison.

The Benefits

Machine learning can be applied to several areas of the overall payment process to proactively prevent fraud. According to the above-cited Teradata case study, the detection of real fraud was increased by 50%. This aids in not only ensuring clients’ accounts remain safe, their information and money intact, but also help lower overhead costs incurred when time is spent on the phone or otherwise helping clients mitigate the fall out of a scam, successful or otherwise.

Some examples of machine learning application include:

  • Better data credibility assessment: Computers can be taught to verify and validate personal details via public sources and transactions history. This helps bridge gaps that might appear in transaction sequences. By reconciling paper documents and system data, machine learning can eliminate the human factor usually required in these scenarios.
  • Evaluate duplicate transactions: Because of the rising speed and number of transactions, a popular scam is to either create a new transaction as close as possible to a valid transaction, or to duplicate an existing transaction to look like a computer or input error. Rule-based systems often fail to distinguish between error or unusual transactions from true fraud. Machine learning, on the other hand, can detect patterns in consumer spending and flag activity that truly seems suspicious. And with the inevitable arrival of more data from which to learn, machines will only get smarter.
  • Mine existing behavior analytics: Much of current fraud detection relies on behavior analytics, which is understanding how a client typically spends their money. This can be expressed in regular visits to ATMs, typical spending patterns shown in times and dates, and other metrics. These metrics provide rich sources of data to train machines on client patterns and what might result or point to a fraudulent transaction.

There are many other benefits, for banks and customers alike:


 

Conclusion

Machine learning offers financial institutions many benefits; it works off of existing data within the company, can increase customer satisfaction, and lessen the amount of work needed to keep accounts and business assets safe. By securing customers’ information and money, a financial organization secures their reputation and their future.

By using existing data sets, banks and other financial institutions can create unique fraud prevention systems that grow with their business and understand their customers on a level that rule-based systems cannot. 

If you’re interested in learning more about what machine learning can do for your bank or financial institution, contact Softjourn today. Our experience with artificial intelligence can help you personalize services and deliver real-time solutions, keeping up with the competition.

1 McKinsey & Company (2018, October). Global payments 2018: A dynamic industry continues to break new ground.
2 McAfee (2018, February). Economic Impact of Cybercrime--No Slowing Down.  
3 Javelin Strategy & Research (2017, February 1). Identity Fraud: Securing the Connected Life.
4 Mejia, N. (2019, October 04). AI-Based Fraud Detection in Banking – Current Applications and Trends

Softjourn is a global technology services provider that finds custom solutions for our clients’ toughest challenges. We leverage our domain expertise in Fintech, Cards & Payments, and Media & Entertainment (with a special emphasis on ticketing), to apply new technology that brings our clients' growing needs to life. Contact us to discuss how we can make your idea a reality!