Comparative Analysis of Supervised Machine Learning Techniques for Sales Forecasting

Abstract

This study talks about how data mining can be used for sales forecasting in retail sales and demand prediction. Prediction of sales is a crucial task which determines the success of any organization in the long run. There are various techniques available for predicting the sales of a supermarket such as Time Series Algorithm, Regression Techniques, Association rule etc. In this paper, a comparative analysis of some of the Supervised Machine Learning Techniques have been done such as Multiple Linear Regression Algorithm, Random Forest Regression Algorithm, K-NN Algorithm, Support Vector Machine (SVM) Algorithm and Extra Tree Regression to build a prediction model and precisely estimate possible sales of 45 retail outlets of Walmart store which are at different geographical locations. Walmart is one of the foremost stores across the world and thus authors would like to predict the sales accurately. Certain events and holidays affect the sales periodically, which sometimes can also be on a daily basis. The forecast of probable sales is based on a combination of features such as previous sales data, promotional events, holiday week, temperature, fuel price, CPI i.e., Consumer Price Index and Unemployment rate in the state. The data is collected from 45 outlets of Walmart and the prediction about the sales of Walmart was done using various Supervised Machine Learning Techniques. The contribution of this paper is to help the business owners decide which approach to follow while trying to predict the sales of their Supermarket taken into account different scenarios including temperature, holidays, fuel price, etc. This will help them in deciding the promotional and marketing strategy for their products.

Applying Machine Learning in Retail Demand Prediction—A Comparison of Tree-Based Ensembles and Long Short-Term Memory-Based Deep Learning

“…In Raizada et al (2021), ETR emerged as the most effective method for forecasting future sales of Walmart stores, closely followed by the random forest regression. Completely in line with our findings, these findings also suggest prioritizing ETR for sales prediction [34], potentially bypassing extensive analyses with alternative supervised machine learning algorithms or avoiding black-box models, like LSTM. Tree ensembles inherently offer a more interpretable structure.…”

“…Ensemble learning techniques, involving the averaging of results from multiple decision trees, show better accuracy. Thus, for such scenarios, business owners are advised to opt for ensemble learning models [34]. Seyedan et al (2022) proposed a demand forecasting methodology for the sports retail industry using ensemble learning.…”

FEDRETAIL: A Framework for Distributed Retail Data Analysis and Learning Toward E-commerce 5.0

“…Churn prediction also attracts the attention of researchers. Raizada et al and Saini et al use retail data mining and different supervised learning techniques to evaluate the accuracy of different prediction models to find the profile of customers who are at risk of churning in a Brazilian e-commerce setting (Raizada & Saini, 2021). Ullah et al use the random forest model and the real data set of Customer Relationship Management (CRM) to identify customers who are likely to churn early and retain them effectively (Ullah et al, 2019).…”

Comparative Analysis of Regression Algorithms used to Predict the Sales of Big Marts

“…It is not computationally expensive. K-NN model of Regression can be implemented in both linear and non-linear relationships [11].…”