A framework for forecasting demand for new services and their cross effects on existing services

Abstract In this article we deal with the problem of forecasting the demand for future new services and existing services simultaneously. When a number of new services are to be introduced into the market, according to our experience, it is very difficult to carry out a market survey and obtain reliable data to facilitate the forecasting. The main difficulty is due to the fact that each new service may have a cross effect on almost every existing service. Moreover, new services are likely to have substitutive and complementary effects on each other. In this article we propose a model which can incorporate these effects. This is accomplished by characterizing each telecommunications service and each telecommunications application by a set of service attributes. The cost (to the customer) of each service is also explicity incorporated. The model parameters are estimated by exploiting the historical customer choice behavior in choosing existing services. The proposed model also allows an investigator to incorporate any foreseen trends of new telecommunications applications (customer needs). This approach has produced reasonable results in our applications.