Flexible Forecasting Model Based on Neural Networks

There is a growing recognition that various planning agencies in warranty system sectors have a significant interest in measuring and forecasting the growth of green warranty claims. The difficulties lie in finding a forecasting model that can incorporate both internal and external influences on green warranty diffusion, as well as an acceptable measure for green warranty growth. This paper uses models based on the knowledge of traditional diffusion theories as well as artificial neural networks. Additionally, it integrates the two into a hybrid model in order to study green warranty growth. A count of warranty claims is used as a reliable measure of green warranty growth in all the models. This paper demonstrates that a simple Neural Network model, if properly calibrated, can create a very flexible response function to forecast green warranty diffusion. The neural network model successfully modeled both the internal and external influences in the warranty data, while the traditional formulations could only model the internal influences. The predictive validation of the results was enhanced by replicating the comparisons on simulated data with various degrees of external influence. This paper suggests that when there are external influences such as green warranty, the neural network model will be superior to the best traditional diffusion model.