How can transaction analytics deliver a major competitive advantage in lending? This is the topic I will be discussing at the Gartner Data & Analytics conference May 9-11 in London. Here’s a preview.
The pandemic highlighted the over-reliance of banks on traditional data when making credit decisions. The sudden nature of the lockdowns had an immediate impact on incomes for consumers and the businesses that supported them. Existing models that were designed for cyclical downturns — rather than a halt in economic activity — are now not as predictive or relevant when considering this historical data and making future decisions.
Given the significant changes in credit and consumer behaviour, there has been a quest by lenders for new data and early warning indicators.
The modern data explosion has the opportunity to provide more accuracy and speed and avoid the lag that comes with some more traditional indicators. The data explosion has also made banks curious about finding new customers and driving financial inclusion. There are an estimated 3 billion adults worldwide who don’t have credit and so don’t have credit records. Opening this market is a priority for lenders. And while many of these people are in developing markets with nascent credit infrastructures, there are plenty of so-called “credit invisibles” in the most mature credit markets as well.
Transaction data can help increase the speed and accuracy of lending for banks. While it may not seem “alternative” as most lenders have this data already, it’s not often mined to extract the maximum predictive value.
Transaction data can be used to generate a wide range of predictive characteristics such as Ratios of Cash to Total Spend in last X week(s) or Ratios of Spend in last X week(s) to last Y week(s) and even characteristics based on the number, frequency and value of transactions at different retailer types. Processing it can be time-consuming, but the data itself is generally clean.
Transaction Analytics – Why Now?
So what is the appeal of transaction data?
Firstly, it offers a highly accessible, real-time indicator of financial health.
Secondly, its use from a practical level has become much easier to manage and leverage for insights. In recent years we have seen computational advances in processing, data orchestration, and feature stores. We have also had numerous mathematical advances in machine learning and explainable AI.
A third advantage is that this data is readily available. Banks have this information about their own customers and in many markets can gain access to new-to-bank customers via open banking frameworks. The ability for lenders to start analysis of transaction flows such as level, frequency and volatility allows them to better track performance and risk in real-time.
The last reasons to look more closely at transactional analytics is that the data meets the regulatory standards of all markets and that can be used at multiple touch points in the decision-making process. For example, it can be used in onboarding a customer, determining a credit limit extension, a recovery treatment and even to pick up suspected fraud.
FICO’s advanced analytics around transactional fraud monitoring are well known in banking. What what’s less known is that its data scientists have applied the same innovative thinking to solutions around the credit risk cycle and how transactional analytics can be used.
FICO’s transaction analytics are delivering significant value to banks looking to improve their model accuracy and reactiveness in today’s challenging markets.
Learn More at the Gartner Conference
At the Gartner Data & Analytics conference. I will be exploring this topic in more detail, and showing results from banks using transactional analytics. If you’re attending, join my session and drop by booth 803 to have a one-to-one discussion.
How FICO Platform Can Help You Achieve Greater Returns from Lending
- Discover the power of FICO Platform to help you drive greater value from lending strategies.
- Read this blog on How Transactional Analytics for SME Lending Drive Greater Value
- Explore Defining Big Data Characteristics – A Data Scientist’s Life Hack