Inspiration

Loyalty programs are to reward repeat customers. A bias is an illogical preference or prejudice. Fraud is a crime in which someone tricks somebody else to get unfair or unlawful gain. Having recognized the bias, vulnerabilities and the increasing fraud in loyalty, we decided to build FinLoyal `

What it does

FINLoyal is an ML powered loyalty management solution that can offer loyalty points and rewards to customers, eliminating all systemic biases & loyalty fraud, ensuring equality to all customers. It also monitors customer transactions and assigns risk scores to each of them, based on which the system identifies possible suspects for loyalty fraud. The relationship manager would then have the option to review such transactions, recalibrate and identify whether there is loyalty fraud or not. Unlike rule-based systems, this solution spot implicit correlations between user behavior and the possibility of fraud and abuse. The solution also employs a linear regression model to identify and eliminate biases while assigning loyalty points. The model attempts to explain the biases/fraud, enabling the relationship manager to take informed decisions.

How we built it

Using below 5 steps of data analytics to predict and detect fraud in Loyalty program

Data Preparation
Leverage from what you already know / Supervised Learning
Predict Loyalty score
Anomaly detection
Integration

Challenges we ran into

Non availability of historic data for training ML models. Hence we have used data from open source platform Kaggle

Accomplishments that we're proud of

Collaborating and networking with the team established as part of FinIndia AI/ML SIG Group with members from across sites Finastra Bangalore, Finastra Trivandram and Finstra Data Team
Integrating with FFDC API
Leveraging the expertise of all the team members of different levels / years of experience

What we learned

Loyalty fraud is on the rise again and, while account takeovers seem to be the most common type of fraud reported, this type of theft is only the tip of the iceberg; program rules violation, unauthorized redemptions, privilege escalations, flawed integrations and data breaches are also on the rise. To complicate matters, the increasing complexity of loyalty programs makes it even harder for companies to defend themselves against fraudsters. A typical project for a loyalty platform implementation involves dozens of integrations with other systems, partners, point transfers, reversals, conversions and so on. The more complex the implementation, the higher the probability that there will be loopholes that can be exploited.

What's next for FINLoyal

We can extend this to a dashboard with accumulated points, reward redeemed, and actionable insights for customers to accumulate more points can enrich FinLoyal Customer experience.