LARGE SCALE RETAIL SALES FORECASTING USING BIGDATA

This paper presented a big data driven retail sales forecasting framework integrating distributed data processing and advanced machine learning models. The proposed system achieves improved forecasting accuracy and scalability in large retail environments.   Future work includes integrating reinforcement learning for dynamic pricing strategies, incorporating real time streaming data for adaptive forecasting, implementing transformer based timeseries models, and enhancing explainability mechanisms for managerial decision support.

[1] Y. Chen et al., “Distributed Machine Learning for Large Scale Retail Sales Forecasting,” IEEE Access, 2023.   [2] M. Kumar et al., “Deep Learning Models for Multi Store Retail Demand Prediction,” IEEE Transactions on Artificial Intelligence, 2024.   [3] L. Zhang et al., “Hybrid Gradient Boosting and Neural Networks for Retail Time Series Forecasting,” IEEE Transactions on Neural Networks and Learning Systems, 2024.   [4] R. Patel et al., “Temporal Convolutional Networks for Multi Step Retail Forecasting,” IEEE Access, 2025.   [5] H. Lee et al., “Scalable Big Data Pipelines for Retail Analytics,” IEEE Internet of Things Journal, 2025.   [6] A. Singh et al., “Explainable AI for Demand Forecasting in Retail,” IEEE Transactions on Artificial Intelligence, 2026.   [7] T. Nguyen et al., “Feature Engineering Strategies for Retail Sales Prediction,” IEEE Access, 2023.   [8] P. Wang et al., “Large Scale Time Series Modeling Using Distributed Learning,” IEEE Transactions on Artificial Intelligence, 2024.   [9] K. Roy et al., “Advanced Ensemble Learning for Retail Forecasting,” IEEE Access, 2025.   [10] J. Brown et al., “RealTime Retail Analytics Using Big Data Technologies,” IEEE Access, 2026.