A novel approach to increase scalability while training machine learning algorithms using Bfloat 16 in credit card fraud detection

TL;DR

This paper proposes a scalable machine learning approach using Bfloat16 precision to improve credit card fraud detection efficiency, reducing training time and costs while maintaining detection performance.

Contribution

It introduces a novel technique leveraging Bfloat16 precision to enhance scalability and reduce costs in credit card fraud detection systems.

Findings

Bfloat16 training reduces model training time

Cost efficiency improves with lower precision training

Detection accuracy remains comparable to traditional methods

Abstract

The use of credit cards has become quite common these days as digital banking has become the norm. With this increase, fraud in credit cards also has a huge problem and loss to the banks and customers alike. Normal fraud detection systems, are not able to detect the fraud since fraudsters emerge with new techniques to commit fraud. This creates the need to use machine learning-based software to detect frauds. Currently, the machine learning softwares that are available focuses only on the accuracy of detecting frauds but does not focus on the cost or time factors to detect. This research focuses on machine learning scalability for banks' credit card fraud detection systems. We have compared the existing machine learning algorithms and methods that are available with the newly proposed technique. The goal is to prove that using fewer bits for training a machine learning algorithm will result in a more scalable system, that will reduce the time and will also be less costly to implement.