Network-based exploratory data analysis and explainable three-stage deep clustering for financial customer profiling

Abstract

Effective customer segmentation and communication of these findings to non-experts is a pressing task in the financial services sector, with the potential for widespread applications. This study employs a three-stage dimension reduction and clustering technique to segment a large, high-dimensional dataset, emphasizing explainability and intuitive visualization. We present the high-dimensional data and feature set using novel network-based visualization methods and identify the multi-stage process's optimal configuration. The approach segments 14,837 potential customers, each with 163 categorical and 143 numerical features. The first stage of the dimension reduction process employs deep neural network-based autoencoders. The second and third stage uses a non-neural network-based dimension reduction algorithm and clustering algorithm contingent on clustering performance. Subsequently, game theory-inspired Shapley values are computed for each feature to enhance explainability. The optimal approach involves an autoencoder, isometric mapping to three dimensions, and K-means clustering. Lastly, we derive investment portfolios for each segment to demonstrate an expert system application in financial investment advisory to underscore the importance of explainable segmentations.