Enhancing Consumer Purchasing Pattern Prediction on E-Commerce Platforms Using Random Forest Algorithm: A Simulation Approach

DOI

10.2991/978-94-6463-982-7_5How to use a DOI?

Keywords

E-commerce; Consumer Purchasing Patterns; Random Forest; Machine Learning; Prediction; Data Mining; Marketing Optimization

Abstract

The rapid expansion of e-commerce has transformed consumer purchasing activities, positioning digital platforms as the dominant medium for modern transactions. However, this growth has also introduced new challenges in analyzing and predicting increasingly complex consumer purchasing behaviors. Manual data analysis is no longer efficient nor scalable, underscoring the importance of machine learning-based predictive approaches. This study employs the Random Forest algorithm to model and predict consumer purchasing patterns using demographic, behavioral, and transactional data. Unlike previous research that primarily utilized descriptive data mining techniques such as FP-Growth or Apriori to identify frequent transaction patterns, this study focuses on predictive modeling to forecast future purchasing decisions. The research methodology includes data collection, preprocessing (handling missing values and standardizing variables), model training, and evaluation using performance metrics such as accuracy, ROC AUC, and F1-Score. The experimental results show that the Random Forest model achieved 69% accuracy and a ROC AUC of 0.77, demonstrating strong discriminative capability between buyers and non-buyers. Feature importance analysis further indicates that transactional attributes—particularly recent orders and gross merchandise value (GMV)—are the most influential predictors. The findings highlight the effectiveness of ensemble machine learning in e-commerce applications and offer actionable insights for improving targeted marketing strategies and customer segmentation. This research contributes novelty by shifting the analytical perspective from descriptive to predictive modeling, enabling a more forward-looking understanding of consumer behavior.

Copyright

© 2025 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  - Dwi Ely Kurniawan
AU  - Tasya Erwina
PY  - 2025
DA  - 2025/12/29
TI  - Enhancing Consumer Purchasing Pattern Prediction on E-Commerce Platforms Using Random Forest Algorithm: A Simulation Approach
BT  - Proceedings of the  8th International Conference on Applied Engineering (ICAE 2025)
PB  - Atlantis Press
SP  - 54
EP  - 72
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-982-7_5
DO  - 10.2991/978-94-6463-982-7_5
ID  - Kurniawan2025
ER  -