AI-ENABLED DEMAND FORECASTING AND INVENTORY OPTIMIZATION IN THE ORACLE CORPORATION ENVIRONMENT
Artificial intelligence (AI) is transforming the supply chain management system by allowing it to make accurate forecasts of demand as well as optimise inventory in an effective manner. The current study examines how AI-based techniques can be applied in a setting that is oriented towards an ERP, where the accuracy of forecasting, as well as inventory decisions, can be enhanced. Through the Online Retail Dataset as a proxy of the transactional data of enterprises, machine learning models such as the Random Forest, the Gradient Boosting, and the Long Short-Term Memory (LSTM) networks were created and tested. The findings show that Gradient Boosting is more accurate and stable in predicting, and an LSTM cannot perform because of the limitations of the data. Outputs of the predictions were then incorporated into an inventory optimization model to calculate safety stock and reorder points to show the real-world effects of AI in helping to eliminate stock inefficiencies and enhance service levels. The results emphasize the significance of data quality, model choice, and integration of systems in achieving the maximum potential of AI in ERP systems. The research is a part of the expanding literature concerning intelligent supply chains and can provide valuable guidelines to apply the AI-driven solutions to enterprise settings.
Authors
- Khurram Shahzad Butt
- Shoaib Muhammad Meo
- Kareemuddin Shahbaaz Khaja
Publication Details
- Journal
- Research
- Published
- 2026-11-21
- DOI
- https://doi.org/10.5281/zenodo.24423204
- Primary Topic
- Forecasting Techniques and Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00