A High-Performance Customer Churn Prediction System based on Self-Attention

TL;DR

This paper introduces a novel hybrid neural network with self-attention (HNNSAE) that significantly improves customer churn prediction accuracy by enhancing feature extraction capabilities, outperforming existing machine learning models.

Contribution

The paper proposes a new hybrid neural network model with self-attention and residual connections for better feature extraction in churn prediction.

Findings

HNNSAE outperforms other machine learning and deep learning methods.

The proposed feature extractor significantly surpasses other methods.

Four hypotheses on model performance and overfitting were validated.

Abstract

Customer churn prediction is a challenging domain of research that contributes to customer retention strategy. The predictive performance of existing machine learning models, which are often adopted by churn communities, appear to be at a bottleneck, partly due to models' poor feature extraction capability. Therefore, a novel algorithm, a hybrid neural network with self-attention enhancement (HNNSAE), is proposed in this paper to improve the efficiency of feature screening and feature extraction, consequently improving the model's predictive performance. This model consists of three main blocks. The first block is the entity embedding layer, which is employed to process the categorical variables transformed into 0-1 code. The second block is the feature extractor, which extracts the significant features through the multi-head self-attention mechanism. In addition, to improve the feature extraction effect, we stack the residual connection neural network on multi-head self-attention modules. The third block is a classifier, which is a three-layer multilayer perceptron. This work conducts experiments on publicly available dataset related to commercial bank customers. The result demonstrates that HNNSAE significantly outperforms the other Individual Machine Learning (IML), Ensemble Machine Learning (EML), and Deep Learning (DL) methods tested in this paper. Furthermore, we compare the performance of the feature extractor proposed in this paper with that of other three feature extractors and find that the method proposed in this paper significantly outperforms other methods. In addition, four hypotheses about model prediction performance and overfitting risk are tested on the publicly available dataset.