Abstract—A top priority in any business is a constant need to increase revenue and profitability. One of the causes for a decrease in profits is when current customers stop transacting. When a customer leaves or churns from a business, the opportunity for potential sales or cross selling is lost. If a customer leaves the business without any form of advice, the company may find it hard to respond and take corrective action. Ideally companies should adopt a proactive and identify potential churners prior to them leaving. Customer retention strategies have been noted to be less costly than attracting new customers. Through data available within the Point of Sales (POS) systems, customer transactions may be extracted and their buying patterns may be analysed. This paper demonstrates how through transactional data features are created and may be identified as significant to predict churn within the retail industry. The data provided within this paper pertains to a local supermarket. Therefore, the churners identified and results attained are based on real scenarios. The novelty of this paper is the concept of implementing deep learning algorithms. Convolution Neural Networks and Restricted Boltzmann Machine are the selected deep learning techniques. The Restricted Boltzmann Machine attained the best results that of 83% in predicting customer churn.
Index Terms—Customer churn, deep learning, retail grocery industry.
Alexiei Dingli and Nicole Sant Fournier are with the Department at University of Malta, Malta (email: alexiei.dingli@um.edu.mt, Nicole.sant-fournier.15@um.edu.mt).
Vincent Marmara is with the Faculty of Economics, Management and Accountancy; University of Malta, and also with Faculty of Business and IT; University of Malta, Malta (email: Vincent.marmara@um.edu.mt).
Cite: Alexiei Dingli, Vincent Marmara, and Nicole Sant Fournier, "Comparison of Deep Learning Algorithms to Predict Customer Churn within a Local Retail Industry," International Journal of Machine Learning and Computing vol. 7, no. 5, pp. 128-132, 2017.