Introducing Economic Order Quantity Model for Inventory Control in Web based Point of Sale Applications and Comparative Analysis of Techniques for Demand Forecasting in Inventory Management

paper has primary focus on the aspect of inventory management in web based point of sale applications for supermarkets. The major research focus include selection of efficient technique for demand forecasting in retail industry, the introduction of Economic Order Quantity model to reduce the overall inventory related costs and stock-out, analyzing customer transactions to improve sales, determining product shelving and supplier selection. For this purpose, Economic Order Quantity model is applied on the forecasted demands using simple moving average, linear regression, back propagation algorithm and afterwards a comparative analysis is conducted on the basis of costs generated by each demand forecasting technique. The comparison shows that back propagation algorithm is more efficient for demand forecasting and the overall inventory costs after applying Economic Order Quantity model are found to be lowest for back propagation algorithm as compared to the Linear Regression and Simple Moving Average. KeywordsAlgorithm, Back Propagation Algorithm, Data mining, Economic Order Quantity model, K-means Algorithm, Linear Regression, Naive Bayesian Algorithm