Artificial neural networks to estimate the forecast of tourism demand in Peru

Abstract

Service companies, for the most part, do not have physical inventories that allow them to cushion demand variability. The high logistics costs of each process of the company are the reflection of these differences in the forecast. For this reason, having a successful demand forecast will generate a competitive advantage in companies that take these processes with interest. In the present work it is possible to estimate the amount of tourist packages that will be sold in the next three months using ANN (artificial neural networks) that present a decrease in the error of the current situation of 9.89% which, together with a forecast management system of adequate demand, it was thus possible to reduce the logistics costs of the services company by up to 33%.