A NAS-Optimized Deep Learning Model for Customer Churn Prediction in Financial Services

• Marcus Almeida UFOP
• Ivair Silva UFOP
• Vander Freitas UFOP
• Eduardo Luz UFOP
• Gladston Moreira UFOP

Resumo

Deep Learning (DL) methods offer competitive alternatives for Customer Churn Prediction (CPP) but are challenging to optimize due to their complexity. This study introduces STArS (Sequential Temporal Neural Architecture Search), a Genetic Algorithm-based Neural Architecture Search (NAS) method, to optimize Temporal Convolutional Neural Networks (TCNN) and Long Short-Term Memory (LSTM) models. The optimized STArS models outperform traditional models, such as Random Forest and XGBoost, as well as an empirically developed TCNN. The research also highlights the importance of feature analysis for retention strategies, using a real dataset from a financial services provider. This demonstrates the practical applicability of NAS techniques across multivariate time series datasets.