Clustering in Recurrent Neural Networks for Micro-Segmentation using Spending Personality

TL;DR

This paper introduces a novel method using recurrent neural networks to extract temporal features for fine-grained customer segmentation based on spending personality, outperforming non-sequential models in micro-segmentation.

Contribution

It demonstrates that recurrent neural networks can effectively produce detailed customer segments and match the performance of specialized models on key financial metrics.

Findings

Recurrent neural networks yield more discriminative micro-segments.

Extracted features from RNNs perform comparably to bespoke models.

Temporal features improve segmentation granularity.

Abstract

Customer segmentation has long been a productive field in banking. However, with new approaches to traditional problems come new opportunities. Fine-grained customer segments are notoriously elusive and one method of obtaining them is through feature extraction. It is possible to assign coefficients of standard personality traits to financial transaction classes aggregated over time. However, we have found that the clusters formed are not sufficiently discriminatory for micro-segmentation. In a novel approach, we extract temporal features with continuous values from the hidden states of neural networks predicting customers' spending personality from their financial transactions. We consider both temporal and non-sequential models, using long short-term memory (LSTM) and feed-forward neural networks, respectively. We found that recurrent neural networks produce micro-segments where feed-forward networks produce only coarse segments. Finally, we show that classification using these extracted features performs at least as well as bespoke models on two common metrics, namely loan default rate and customer liquidity index.