International Journal For Multidisciplinary Research

E-ISSN: 2582-2160     Impact Factor: 9.24

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Call for Paper Volume 7, Issue 4 (July-August 2025) Submit your research before last 3 days of August to publish your research paper in the issue of July-August.

Explainable AI (XAI) for Cloud Resource Forecasting in E-Commerce Environments

Author(s) Mr. Sudheer Singh, Mr. Vasudev Karthik Ravindran, Mr. Sambhav Patil
Country India
Abstract The rapid growth of e-commerce has intensified the demand for accurate and trustworthy cloud resource forecasting to ensure seamless service delivery during volatile and unpredictable workload fluctuations. Traditional black-box machine learning models, while powerful in prediction, often fail to provide the transparency necessary for stakeholders to trust and effectively manage automated resource allocation decisions. This paper proposes a novel hybrid framework that integrates Explainable Artificial Intelligence (XAI) techniques into cloud resource forecasting for e-commerce environments, combining the predictive strength of advanced sequential models like LSTM with interpretable surrogate models and post-hoc explanation methods such as SHAP and LIME. Using real-world workload data from a leading e-commerce platform, the study demonstrates that the hybrid model achieves superior predictive performance—reflected by lower RMSE, MAE, and MAPE values—while delivering clear, actionable explanations that align with stakeholders’ operational knowledge. Experimental results under realistic scenarios, including high-demand events like flash sales, confirm that embedding explainability into forecasting pipelines enhances operational trust, supports proactive resource provisioning, and aligns with emerging requirements for AI transparency and accountability. The findings advocate for a shift from opaque forecasting systems to transparent, interpretable frameworks that bridge the gap between technical accuracy and responsible AI governance, laying a robust foundation for future advancements in intelligent, ethical cloud resource management in dynamic digital commerce landscapes.
Keywords Explainable AI, Cloud Resource Forecasting, E-Commerce Workloads, Interpretability, Hybrid Machine Learning
Field Computer > Logic
Published In Volume 7, Issue 4, July-August 2025
Published On 2025-07-25
DOI https://doi.org/10.36948/ijfmr.2025.v07i04.51796
Short DOI https://doi.org/g9vpj9

Share this