Temporal Knowledge Distillation for Time-Sensitive Financial Services Applications

TL;DR

This paper introduces a temporal knowledge distillation method that accelerates model retraining in financial anomaly detection, enhancing responsiveness to evolving threats while maintaining high detection performance.

Contribution

The paper presents a novel temporal knowledge distillation approach that reduces retraining times and improves model agility in time-sensitive financial anomaly detection tasks.

Findings

Reduces model retraining times significantly

Improves anomaly detection performance

Enhances model responsiveness to data changes

Abstract

Detecting anomalies has become an increasingly critical function in the financial service industry. Anomaly detection is frequently used in key compliance and risk functions such as financial crime detection fraud and cybersecurity. The dynamic nature of the underlying data patterns especially in adversarial environments like fraud detection poses serious challenges to the machine learning models. Keeping up with the rapid changes by retraining the models with the latest data patterns introduces pressures in balancing the historical and current patterns while managing the training data size. Furthermore the model retraining times raise problems in time-sensitive and high-volume deployment systems where the retraining period directly impacts the models ability to respond to ongoing attacks in a timely manner. In this study we propose a temporal knowledge distillation-based label augmentation approach (TKD) which utilizes the learning from older models to rapidly boost the latest model and effectively reduces the model retraining times to achieve improved agility. Experimental results show that the proposed approach provides advantages in retraining times while improving the model performance.