Please use this identifier to cite or link to this item:
Title: Evaluating deep learning and machine learning techniques to predict customer churn within a local retail industry
Authors: Sant Fournier, Nicole
Keywords: Customer relations
Consumer satisfaction
Machine learning
Retail trade
Issue Date: 2018
Citation: Sant Fournier, N. (2018). Evaluating deep learning and machine learning techniques to predict customer churn within a local retail industry (Master's dissertation).
Abstract: A top priority in any business is a constant need to increase revenue and profitability. Within the retail industry, the main source of revenue is based on the purchases of customers. For this reason, companies need to focus on customer retention. When a customer leaves or churns from a business, the opportunity for potential sales or cross selling is lost. When a customer leaves the business without any form of explanation or notice, the company may find it hard to respond and take corrective action. Ideally companies should be proactive and identify potential churners prior to them leaving. Customer retention has been noted to be less costly than attracting new customers. Therefore, identifying individuals that are likely to churn is of great benefit to the company. Through data available within the Point of Sales (POS), customer transactions may be extracted and buying patterns may be identified. This project demonstrates how through transactional data, features are created and may be defined as significant in predicting churn. By predicting churn, companies may adopt a proactive approach to retaining customers. The data provided within this project pertains to a local supermarket. Therefore the results attained through the various models are based on true data. The novelty of this dissertation is the concept of implementing and comparing Deep Learning algorithms to Machine Learning techniques. Convolution Neural Networks, Deep Neural Networks and Restricted Boltzmann Machine are the selected Deep Learning techniques, whilst Random Forest and Logistic Regression are implemented as Machine Learning algorithms. Furthermore, various datasets are designed to evaluate how the mentioned algorithms perform based on the features designed. The overall accuracy results obtained for the mentioned algorithms are: Random Forest attained an 94%, Restricted Boltzmann Machine obtained 83%, Logistic Regression acquired 77% and Convolution Neural Network attained 74%. The results are satisfactory and may contribute in assisting the supermarket in retaining customers.
Appears in Collections:Dissertations - FacICT - 2018
Dissertations - FacICTAI - 2018

Files in This Item:
File Description SizeFormat 
  Restricted Access
2.95 MBAdobe PDFView/Open Request a copy

Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.