Predicting E-Commerce Sales with Three Machine Learning Models

DOI

10.2991/978-94-6463-542-3_52How to use a DOI?

Keywords

Machine Learning Models; Sales Prediction; E-Commerce Sales

Abstract

Online shopping has gained popularity with the advent of e-commerce, owing to its convenience, wide range of choices, and reduced geographical limitations. At the same time, competition among e-commerce enterprises has become increasingly fierce, so enhancing the core competitiveness of e-commerce companies is now contingent upon accurately predicting future sales and devising rational sales strategies. Machine learning (ML) techniques play a pivotal role in this process, as they efficiently handle intricate data and reveal underlying patterns within sales figures, thereby enabling precise projections of upcoming trends. By harnessing the power of ML, e-commerce enterprises can gain a competitive edge and stay ahead of the curve in today’s dynamic market. In this paper, sales data on the e-commerce platform of an online retail store registered in the United Kingdom are used to make e-commerce sales predictions employing three distinct ML models: Linear Regression (LR), Decision Tree (DT), and Random Forest (RF). Subsequently, the performance of these models is evaluated by calculating their Mean Absolute Error (MAE), Mean Square Error (MSE), and R-squared values. The selection of the optimal sales prediction model was based on the fitness of the prediction results obtained from each model. By comparing these three regression evaluation metrics, particularly R-squared, the model with the largest R-squared is selected as the one that predicts sales most accurately.

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  - Xinyan Li
PY  - 2024
DA  - 2024/10/15
TI  - Predicting E-Commerce Sales with Three Machine Learning Models
BT  - Proceedings of the 2024 2nd International Conference on Management Innovation and Economy Development (MIED 2024)
PB  - Atlantis Press
SP  - 445
EP  - 454
SN  - 2352-5428
UR  - https://doi.org/10.2991/978-94-6463-542-3_52
DO  - 10.2991/978-94-6463-542-3_52
ID  - Li2024
ER  -