Optimization of SCM process using evolutionary algorithm on SVR

Demand forecasting is estimation of demand depending upon the sales data or the previous demand data. Forecasting demand accurately is a herculean task. Demand Forecast depends upon factors such as the seasonal trend, price elasticity of product. Supply Chain Management (SCM) process includes task like procuring goods, inventory, and manufacture, planning logistics, facility location, shipping and dissemination. All these functions are affected in the short run by product demand and in the long run by products and processes and fluctuating markets. Forecast of product demand determines quantity of product to be made and how much material to purchase from suppliers to meet forecasted customers' needs. The objective is to predict the demand on daily basis taking previous two days data to predict the third day. By using Support Vector Regression (SVR) for predicting the demand and optimize its parameters using Artificial Bee Colony (ABC).