Irshadullah Asim Mohammed
Research Subjects
Irshadullah Asim Mohammed has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Ashok Dattatraya Todmal
MIT College of Management, MIT Art Design and Technology University
2 shared publications - Ganeshavishwaa Veluswwamy Radhakrishnan
Kalinga School of Management, Kalinga Institute of Industrial Technology, Bhubaneswar, India
2 shared publications Pranav Pandurang Gaikwad
University of Cumberlands
2 shared publicationsSri Harsha Vardhan Sanne
EPAM Systems
2 shared publications- Vivek Pimplapure
Dr. Ambedkar Institute of Management Studies and Research
2 shared publications - .P. Sundara BalaMurugan
St. Joseph's Institute of Technology, OMR
1 shared publication
Latest Publications
- Retraction
- 1 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1
Retraction Notice: AI-Based Demand Forecasting System for Supply Chain Optimization
- 1 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1
RetractionRetraction Notice: AI-Based Demand Forecasting System for Supply Chain Optimization
- Retracted
- 1 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
Retracted: AI-Based Demand Forecasting System for Supply Chain Optimization
Successful demand forecasting is a key sector in boosting the efficiency and robustness of contemporary supply chains. This paper introduces an AI-based demand forecasting system that has been implemented to streamline supply chain operations by applying sophisticated machine learning methods and data analytics. The system incorporates sales history, current market sentiment, and external events such as weather and economic conditions to make highly accurate demand forecasts. In contrast to traditional forecasting methods, which often rely on linear models and data, the AI method can accommodate complex, non-linear supply chain patterns. The architecture is a hybrid deep learning model that utilizes Long Short-Term Memory (LSTM) networks and ensemble learning methods to address the temporal dependency and heterogeneity of the data. Experimental testing on actual datasets from real business firms in the manufacturing and retail industries demonstrates improved prediction accuracy to a considerable extent, reducing errors by as much as 25% compared to statistical models. Additionally, the system's predictive forecasts enable companies to minimize inventory expenses, enhance order fulfillment rates, and anticipate supply-demand imbalances, allowing them to respond accordingly. The study also highlights the scalability and flexibility of the proposed system across various supply chain functions, noting its ability to facilitate strategic decision-making. By incorporating AIbased forecasting into supply chain operations, organizations can achieve greater operational efficiency, reduce waste, and enhance customer satisfaction. The findings confirm the system's ability to serve as an effective solution for handling uncertainty in the modern business world.
- 1 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
RetractedRetracted: AI-Based Demand Forecasting System for Supply Chain Optimization
Successful demand forecasting is a key sector in boosting the efficiency and robustness of contemporary supply chains. This paper introduces an AI-based demand forecasting system that has been implemented to streamline supply chain operations by applying sophisticated machine learning methods and data analytics. The system incorporates sales history, current market sentiment, and external events such as weather and economic conditions to make highly accurate demand forecasts. In contrast to traditional forecasting methods, which often rely on linear models and data, the AI method can accommodate complex, non-linear supply chain patterns. The architecture is a hybrid deep learning model that utilizes Long Short-Term Memory (LSTM) networks and ensemble learning methods to address the temporal dependency and heterogeneity of the data. Experimental testing on actual datasets from real business firms in the manufacturing and retail industries demonstrates improved prediction accuracy to a considerable extent, reducing errors by as much as 25% compared to statistical models. Additionally, the system's predictive forecasts enable companies to minimize inventory expenses, enhance order fulfillment rates, and anticipate supply-demand imbalances, allowing them to respond accordingly. The study also highlights the scalability and flexibility of the proposed system across various supply chain functions, noting its ability to facilitate strategic decision-making. By incorporating AIbased forecasting into supply chain operations, organizations can achieve greater operational efficiency, reduce waste, and enhance customer satisfaction. The findings confirm the system's ability to serve as an effective solution for handling uncertainty in the modern business world.