Application of artificial neural networks using bayesian training rule in sales forecasting for furniture industry

Abstract

Most organizations in manufacturing environments aim to increase their profits and reduce costs against competitive and rapidly changing market conditions. Accuracy of sales forecasting is undoubtedly a successful way to reach the aforementioned goals. At the same time, this enables executives to improve customer satisfaction, reduce lost sales and plan production efficiently. As a growing industry in Turkey, furniture manufacturing has an increased product demand in relation to the recent growth in construction and related industries, increase in urban population and increase in person-level income. Therefore, accurate sales forecasting systems in this industry are more focused on the special and calendar factors, such as consumer confidence index, producer price index, time of the year and number of vacation days. In this paper, an artificial neural network (ANN) based forecasting model is proposed by using MATLAB for processing total monthly sales data of a corporate furniture manufacturer located in the Black Sea region of Turkey. The method is a component of ANN, namely Bayesian regularization. The proposed model is applied to monthly sales figures of a corporate furniture manufacturing company. In conclusion, the results of performance measures show that using the ANN model based on Bayesian rules training is an applicable choice for forecasting of monthly sales of the observed furniture factory.