Abstract: This paper is intended to present a digital structure able to forecast the demand of articles in a daily time span and form these forecasts an advice of replenishment orders, in such a way that forecasted incoming sales are always satisfied and stock outs avoided. The quality of this system is evaluated through a simulation process that bases its decisions in data coming from a large retail store and through on field operation in a smaller retail store. In both cases, results show a good performance of the proposed model, with substantial sales increase and costs decrease. All the above, plus the estimation of useful theoretical results, leads to a second part to present a choice support tool for replenishment orders. As this second model makes use of pre-existing ones and adjusted results of these two models allied to possible statistical simulations of the incoming orders’ behaviour, it is expected an easy implementation in any retail company at no or low cost. Therefore, despite this later solution doesn’t put forward a huge technological solution with great consequences over the existing job structure in the retailer, it can still be considered an improvement in the forecasting of incoming orders.
The digital structure proposed in the first part can significantly increase the accuracy of forecasts with several advantages behind it. However, in spite of the clear advantages of the proposed digital structure, it also represents a huge change concerning the structure and information flow within the retailer, with many risks of instability and huge working effort behind it. The same change brought significant no-forecast problems in the past, with severe consequences. Therefore, it was decided to propose a second part based on the assumption that the proposed model will show desirable results. First targets with this goal are a day to day analysis of the existing filling rate levels, in order to check that the given product supply level is correctly pursued, and of the weeks with bigger tumbles in order to analyze the stock outs and control promotions.
Keywords: Predictive Inventory Management, Machine Learning in Retail, Digital Supply Chain Infrastructure, AI-Driven Inventory Optimization, Retail Demand Forecasting, Smart Inventory Systems, ML-Based Stock Replenishment, Real-Time Inventory Analytics, Retail Data Infrastructure, Cloud-Based Inventory Solutions, Inventory Prediction Algorithms, Retail Forecasting Models, Automated Inventory Control, Big Data Inventory Management, Intelligent Stock Management.
|
DOI:
10.17148/IJARCCE.2021.101276
