Clustering in Recurrent Neural Networks for Micro-Segmentation using Spending Personality
This addresses the challenge of elusive micro-segmentation for banks, offering an incremental improvement over existing methods.
The paper tackled the problem of fine-grained customer segmentation in banking by extracting temporal features from recurrent neural networks (LSTM) to predict spending personality from financial transactions, resulting in micro-segments that perform competitively on metrics like loan default rate and customer liquidity index.
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.