A comparison of four machine learning algorithms to predict product sales in a retail store

No Thumbnail Available
Ofoegbu, Kenneth
Issue Date
MSc in Data Analytics
Dublin Business School
Items in eSource are protected by copyright. Previously published items are made available in accordance with the copyright policy of the publisher/copyright holder.
Controlling the retail market is the secret to sustainability in today's business world. Many business entities depend heavily on historical data and product demand projection of sales patterns. The accuracy of these projections has a significant effect on business. Data mining techniques are effective tools for retrieving concealed information from large datasets to increase predictions' precision and reliability. The systematic research and review of comprehensible machine learning classification models to boost product sales predictions are carried out in this work. The traditional statistical forecasting/predicting methods are challenging to cope with big data and accuracy in predicting product sales. However, these problems can be addressed through the use of different data mining and machine learning techniques. In this work, we briefly analyzed sales data and the prediction of product sales. Various techniques used in machine learning and data mining are discussed in the latter part of the research. For the performance evaluation, the best-suited classification model is proposed for the product sales type prediction. The findings are presented in terms of the reliability and accuracy of the different prediction algorithms used. The study shows that the best fit model is Random Forest, which produced the prediction's highest accuracy.