Web Service Based Food Additive Inventory Management with Forecasting System

Abstract

Recently, food industries have been growing rapidly due to the development of novel technology. Numerous research has been conducted to improve products to satisfy the needs of customers. As a result, various food additives have been used to compose the product and which makes it difficult in recognizing and managing food additive stock. To be able to survive in a competitive world, the industry must find a practical stock management solution since under-stocking causes the industry to lose an opportunity to sell while overstocking causes a deficit. This paper focuses on an inventory management and a stock forecasting system. Web service was implemented as a new approach for an inventory management system that helps to manage and to find the food additives that exist in the international food additive database authorized by Codex Alimentarius Commission. Using web services has many advantages than a traditional web base. The service provider does not have to reveal the database access method to the client, and the information or business model can be changed at any time, and no need to update the client side. The client can access the service via any platform. The web service has been developed through Hypertext Mark up Language 5 (HTML5), Node JavaScript (NodeJS), and My Structured Query Language (MySQL), Database Management System, Hypertext Preprocessor (PHP). The stock forecasting was done by Python with four machine learning models which are Naive Bayes, Decision Tree, Linear Regression and Support Vector Regression to predict stock of food additive. Accuracy is used to measure the performance of these techniques. The experimental result indicated that the most accurate model for stock forecasting is Linear regression.