Demand Forecasting Of Engine Oil For Automotive And Industrial Lubricant Manufacturing Company Using Neural Network

In this paper, a case of demand forecasting for engine oil for automotive and industrial lubricant manufacturing company has been presented. It has been observed that the demand for engine oil mainly depends on three factors i.e. quality, cost, and delivery time. These factors are studied and compared with other competitors dealing in similar nature of products. The quality is associated with three sub-parameters viz. poor, same, and better. Similarly, the cost is mapped with three sub-parameters viz. more, equal & less. Delivery time is linked with two sub-parameters viz. long and short. An artificial neural network model is built on the basis of these causal factors. First, the raw data of demand for a period of past 36 months is collected from supply chain managers of the automotive company. The data for a period of 24 months is utilized to train, validate, and test the model. The next twelve month data is predicted by the trained neural network model. After that, the root mean square error is calculated by comparing the predicted data with the rest 12-month available data. The root mean square error is checked for many cases by manipulation of a number of layers and number of neurons at different locations of the network. The result shows predictions made by the neural network model are in tune with the actual demand given by supply chain managers of automotive and industrial lubricant manufacturing company. Thus, the built neural network model can be utilized for accurate & precise future demand predictions for engine oils. (C) 2019 Elsevier Ltd. All rights reserved.