Online NEAT for Credit Evaluation -- a Dynamic Problem with Sequential Data

TL;DR

This paper applies an online neuroevolution approach, NEAT, to credit evaluation with streaming data, introducing enhancements for online learning challenges like data imbalance and computational efficiency.

Contribution

It adapts NEAT for online credit scoring, addressing data imbalance, computational costs, and model stability in streaming environments.

Findings

NEAT outperforms traditional ML methods in online credit evaluation.

Enhanced NEAT handles unbalanced streaming data effectively.

The approach maintains model stability over time.

Abstract

In this paper, we describe application of Neuroevolution to a P2P lending problem in which a credit evaluation model is updated based on streaming data. We apply the algorithm Neuroevolution of Augmenting Topologies (NEAT) which has not been widely applied generally in the credit evaluation domain. In addition to comparing the methodology with other widely applied machine learning techniques, we develop and evaluate several enhancements to the algorithm which make it suitable for the particular aspects of online learning that are relevant in the problem. These include handling unbalanced streaming data, high computation costs, and maintaining model similarity over time, that is training the stochastic learning algorithm with new data but minimizing model change except where there is a clear benefit for model performance