Machine and Deep Learning Applications for Inventory Replenishment Optimization

Inventory replenishment is the process of obtaining the items, components, and raw materials required to make and sell products. It guarantees that items and resources are acquired and delivered in an efficient and timely manner. Poorly managed inventory replenishment can have a severe influence on customers and the overall health of a business, which may result in lost revenue, reduced profits and damaged reputation. Implementing the correct inventory replenishment helps manufacturers and sellers in avoiding major issues such as stock-outs, delayed deliveries and overstocking. Accuracy of forecasting is therefore crucial to retailers' profitability. Fashion businesses need precise and accurate sales forecasting tools to prevent stock-outs and maintain a high inventory fill rate. This thesis navigates the complex landscape of fashion retail forecasting, addressing the challenges posed by intermittent time series data and stock management. Advanced forecasting models have been implemented to account for the intermittent nature of fashion product demand, resulting in predictions more accurate and reliable.The study extends also to stock replenishment strategies, emphasizing the importance of the reorder point, the Cycle Service Level and the safety stock. Lastly, it culminates in the development of a replenishment algorithm aimed at reducing stock-outs, which is a modified version of the Periodic Review Policy: Order-Up-To-Level, now tailored to the sporadic nature of intermittent demand.