Comparative Analysis Of Artificial Intelligence Models For User Behavior Prediction In Big Data-Driven Information Systems
DOI:
https://doi.org/10.31316/astro.v4i2.8428Abstract
In the era of digital transformation, Artificial Intelligence (AI) plays a pivotal role in enabling intelligent, data-driven information systems. This study presents a comprehensive comparative analysis of AI models: Decision Tree (DT) and Artificial Neural Network (ANN), for user behavior prediction within simulated big data environments, specifically in the e-commerce domain. Using 1,000 synthetic sessions that mimic real-world user activities, the study evaluates model performance using classification metrics such as accuracy, precision, recall, and F1-score. ANN outperforms DT across all metrics, achieving 87.2% accuracy and demonstrating superior learning efficiency and generalization. To complement the evaluation, a Long Short-Term Memory (LSTM) model is employed for time-series prediction, yielding a low MAPE of 1.12%, confirming its effectiveness in capturing sequential patterns. The findings offer valuable insights into AI model selection for adaptive and predictive information systems, with implications for developers and researchers seeking to enhance system responsiveness and personalization.
Downloads
Published
How to Cite
Issue
Section
Citation Check
License
Copyright (c) 2025 Faqihuddin Al Anshori, Muhammad Fairuzabadi, Mohd Nasrun Mohd Nawi
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- The journal allow the authors to hold the copyright without restrictions and allow the authors to retain publishing rights without restrictions.
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlike 4.0 International License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
