A Review of Machine Learning for Predicting Supply Chain Demand in Retail
This review aims to demonstrate the effectiveness of the ML and DL approaches to demand forecasting in the retail supply chain, proving the superiority of the approaches over conventional statistical methods. Traditional models suit themselves poorly in the face of nonlinear dependencies, outside influences and fluctuating settings, especially in retail. At the same time, Machine Learning methodologies like RandomForest, SVMs, LSTM, and CNN provide astonishing accuracy once the temporal and spatial complexity characteristics of sales information are discovered. The review underlines the consideration of data fusion and feature construction, including macroeconomic indexes, weather, and promotions, in extending the forecasts. Issues like data quality, scalability and interpretability of the model are deliberated upon along with the solutions related to incorporating IoT and blockchain. These innovations imply real-time data capture, high-reliability levels and greater process transparency. On the same note, using enhanced value assessment indicators, usually MAE, RMSE, and MAPE, highlights that model engineering requires careful, distinct selection methods. Thus, this systematic review has put together and analyzed the most recent developments, issues, and trends in applying ML and DL in enhancing inventory management, pricing, and customer satisfaction in the retail industry to stimulate better performance and competitiveness in today's fast-growing market environment.
Volume & Issue
Vol. Volume 3 / Iss. Issue 1