Econometric Modeling vs Artificial Neural Networks : A Sales Forecasting Comparison
Dinesh Bajracharya · Borås Academic Digital Archive (University of Borås) · 2011
Econometric and predictive modeling techniques are two popular forecasting techniques. Both of these techniques have their own advantages and disadvantages. In this thesis some econometric models are considered and compared to predictive models using sales data for five products from ICA a Swedish retail wholesaler. The econometric models considered are regression model, exponential smoothing, and ARIMA model. The predictive models considered are artificial neural network (ANN) and ensemble of neural networks. Evaluation metrics used for the comparison are: MAPE, WMAPE, MAE, RMSE, and linear correlation. The result of this thesis shows that artificial neural network is more accurate in forecasting sales of product. But it does not differ too much from linear regression in terms of accuracy. Therefore the linear regression model which has the advantage of being comprehensible can be used as an alternative to artificial neural network. The results also show that the use of several metrics contribute in evaluating models for forecasting sales.