Sales Forecasting Using Machine Learning Methods for Online Store

DOI

10.2991/978-94-6463-589-8_6How to use a DOI?

Keywords

Sales Forecasting; Exploratory Data Analysis; Retail; Supervised Methods

Abstract

Sales forecasting is a strategic activity that involves projecting future sales for goods or services in assisting businesses in making educated inventory decisions, increasing operational efficiency, and improving the overall supply chain. Leveraging machine learning and data analytics, sales forecasting can benefit significantly in making accurate sales projections from historical data. This paper highlights the Exploratory Data Analysis (EDA) and feature selection using Recursive Feature Elimination (RFE) process to identify relationships and key features affecting sales. This paper identified important patterns and relationships from retail store context hence, revealed key variables which affected sales which are holidays, promotions, assortments and competition. Hypotheses of multiple relationships manage to be further analysed to utilise data for further model development. This paper used the approach of XGBoost that is able to model sales with accuracy of 98.23%. The forecasted model further strengthens its results through benchmarking against evaluation metrics of Root Mean Squared Error (RMSE), Normalised Root Mean Squared Error (NRMSE), Kolmogorov Smirnov (KS) distance and Pearson Correlation Coefficient (PCC). The trend projections of each variable affecting store and product sales are visualised using a user-friendly dashboard for easy comprehension in extracting key takes from the extracted relationships. This analysis can benefit retail companies by offering a keen insight for better understanding of sales impact factors.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Nur Adlina Mohd Shahar
AU  - Sofianita Mutalib
AU  - Shamimi A. Halim
AU  - William Ramdhan
PY  - 2024
DA  - 2024/12/01
TI  - Sales Forecasting Using Machine Learning Methods for Online Store
BT  - Proceedings of the International Conference on Innovation & Entrepreneurship in Computing, Engineering & Science Education (InvENT 2024)
PB  - Atlantis Press
SP  - 41
EP  - 52
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-589-8_6
DO  - 10.2991/978-94-6463-589-8_6
ID  - Shahar2024
ER  -