A Predictive Analysis of Retail Sales Forecasting using Machine Learning Techniques

Abstract

Sales forecasting is vital to supply chain management and operations between retailer andmanufacturers in the retail industry. The abundant growth of digital data has minimized the traditionalsystem and approaches to a specific tasks. Sales forecasting is the most challenging task for theretail industry's inventory management, marketing, customer service, and business financialplanning. In this paper, we performed a predictive analysis of retail sales of the Citadel POS datasetusing different machine-learning techniques. We implemented different regression (Linear regression,Random Forest Regression, Gradient Boosting Regression) and time series models (ARIMALSTM), models for sale forecasting, and provided detailed predictive analysis and evaluation. Thedataset used in this research is obtained from Citadel POS (Point Of Sale) from 2013 to 2018, acloud-based application that facilitates retail stores to carry out transactions, manage inventories,customers, vendors, view reports, manage reports, manage sales, and tender data locally. The resultsshow that Xgboost outperformed time series and other regression models and achieved the best performancewith an MAE of 0.516 and RMSE of 0.63.