Electronics Spare Part Goods Demand Forecasting Using Markov Model

Abstract

Customer demand forecasting plays an essential part in inventory management in retail companies. Accurate customer demand forecasting will increase a company's competitiveness and play a crucial role in making the right decisions for inventory management. Without demand estimation, products are often purchased more than needed, resulting in overstock or understock product storage in the warehouse. In this paper, we present the results of the Markov Chain method for predicting the quantity of demand for goods in the future to assist decision-making regarding the procurement of commodity goods within the company, especially in the procurement of electronics spare parts in retail companies. This study aims to develop a software-based forecasting system for retail companies using the Markov Model with predictive capabilities. The system will also provide purchasing quantity recommendations to fulfill the stock, calculated from the minimum stock and forecasted demand from customers and suppliers. Using the Markov Chain model, this study predicts electronics spare parts demand using data on item sales during 2022 in a retail company. The forecasting of electronics spare part demand resulted in 88.2% accuracy. The software-based forecasting system has been implemented and tested using black box testing. The testing result shows that the Markov forecasting system is feasible and can be used as a reference in providing electronics spare parts purchasing recommendations for retail companies.

Keywords

• forecasting
• inventory management
• markov chains
• purchase recommendation