Service-demand-forecasting method using multiple data sources

Abstract

A service-demand-forecasting method that uses multiple data sourcesfor improved accuracy is presented in this paperWe presented a advanced scenario simulation framework to analyze each customer service choice behavior and total service demand under an assumed condition. To estimate the demand on service, especiallyfor a new service, scenario simulation is executed based on stated preference data (SP). However, there is usually a considerable gap between an estimate based on SP and the actual outcome. Furthermore, the distribution of attributes of users collected in market surveys is not equal to that ofactual market users, and there is a bias between collected data and attributes ofusers in the market. In this paper, we propose an adjusting method that can re-estimate demands by analyzing the difference between actual and estimated results. We consider the problem ofchoosing an Internet access line service to evaluate the method.An application example shows that distribution differences between areas with respect to customer attributes strongly affect actual market shares.

Mobile-carrier Choice Modeling Framework Under Competitive Conditions

“…It is impossible to analyze the demand of services or products only by using customer choice-behavior models. We proposed a Framework for Scenario Simulation (FSS) to analyze market structure and estimate service demand [6], [7], [8], [9], [10], [11], [12], [13], [14], [15]. The objective of the FSS is not to obtain a demand-forecasting result but to simulate scenarios under assumed conditions according to service changes.…”

“…Several types of discrete choice modeling have been studied for telecommunication services in Japan [4], [5]. We have proposed service choice models to predict the service choice probability under competitive conditions on the basis of Discrete Choice Models [6], [7], [8], [9]. In general, observed variables such as charge, functions and performance are used as explanatory variables in these models.…”

Customer Segmentation in Mobile Carrier Choice Modeling

“…The scenario means a future assumed condition of the market. According to the scenario, the probability of a service being chosen is determined, and by aggregating the probabilities, the service demand is obtained for an assumed scenario [8].…”

“…x Impressive factors x Functional factors x Charge menu dependent factors x Family & friend dependent factors It is found that customers belong to several segments (Cluster ID2, 3,4,6,8) change the current mobile carrier by a major reason.…”

Broadband Demand Analysis for Network Building

“…From the market structure point of view, there has been research related to a framework for scenario simulation [11]- [13], the objective of which is not to obtain a demand forecast, but to simulate scenarios by sensitivity analysis under assumed conditions. This framework needs to construct a service-choice behaviour model based on discrete choice analysis [14].…”