{"id":3597,"date":"2024-07-11T11:24:26","date_gmt":"2024-07-11T09:24:26","guid":{"rendered":"https:\/\/nepttp.avidakizomba.co.za\/?p=3597"},"modified":"2025-06-09T12:09:54","modified_gmt":"2025-06-09T10:09:54","slug":"evaluating-banking-customer-churn-deep-learning-model-deep-neural-network-in-terms-of-explainability","status":"publish","type":"post","link":"https:\/\/www.escience.ac.za\/index.php\/2024\/07\/11\/evaluating-banking-customer-churn-deep-learning-model-deep-neural-network-in-terms-of-explainability\/","title":{"rendered":"Evaluating banking customer churn Deep Learning model (Deep Neural Network) in terms of explainability"},"content":{"rendered":"

Researcher: <\/strong>Hlayisani Khoza, University of Limpopo
Supervisor: <\/strong>Dr Hairong Bau, University of the Witwatersrand, Johannesburg<\/p>

In the financial industry forecasting, client attrition is critical. The expense of hiring fresh clients is significantly greater than the expense of maintaining current clients. There are several Machine Learning (ML) models in use to forecast client attrition, and the results are impressive. The issue with these models is their lack of openness and interpretability. Deep Learning (DL) models are the leading models in this development because of the layered non-linear structure, which provides no insight into how they reach at their results, these strong models have been dubbed \u201cBlack Boxes\u201d. To deal with this problem Explainable methods have been used to explain these model outcomes. In this research, Shapley Additive method has been applied to the Multilayer Perceptron model to explain its result and it has been found to explain banking customer churn better.<\/p>

\n