Font Size: a A A

Research On Forecasting Model Of Telecom Business Income Based On TEI@I Methodology

Posted on:2019-06-24Degree:MasterType:Thesis
Country:ChinaCandidate:D ZhaoFull Text:PDF
GTID:2359330545958244Subject:Business Administration
Abstract/Summary:PDF Full Text Request
The telecommunications industry is a basic industry in China's social economy.It plays an important role in promoting national economic growth,ensuring information security and serving the national network power.With economic growth and technological iterations,the telecommunications industry has maintained a good trend of development despite repeated restructuring and market-oriented reforms.But in recent years,under the influence of the implementation of the industry reform policy,the development of Internet technology and the aggravation of market competition,the whole industry is facing transformation.In this context,it is more valuable to effectively predict the future development of the telecommunications industry and to build a reasonable prediction model.Based on the TEI@I methodology,this paper selects the economic index of telecom business income.According to the development characteristics of the telecom industry,we set up an integrated prediction model based on the annual and monthly two sets of data.For the larger sample monthly service revenue data,we first use seasonal ARIMA model to do linear fitting,get the estimated value sequence and nonlinear residual sequence,estimate the residual sequence by NAR neural network,and finally get the prediction result by linear integration.For the small sample annual telecom business income data,two linear models are established:multiple regression and grey GM(1,1),and support vector machine is applied to integrate nonlinear mapping to get prediction results.Finally,the accuracy of the model is judged according to the integrated models.In contrast,the prediction model based on the TEI@I methodology proposed in this paper can effectively improve the prediction performance of the model and reduce the prediction error.Through this research,at the theoretical level to propose a new way of prediction model of telecom business revenue,make up for the shortage of the monthly data forecast research of the former telecom business income;in practice,the research can provide the basis for the government to formulate relevant policies of telecom business income forecast,auxiliary Telecom Enterprise development strategy.
Keywords/Search Tags:forecasting model of telecom business income, TEI@I methodology, integrated prediction model, time series prediction
PDF Full Text Request
Related items