Using Machine Learning Technique for Telecom Service Providers in Malaysia to Prioritize Broadband Investment in Urban and Rural Areas

The companies that provide telecommunication services (Telco) in Malaysia commonly use the return on investment (ROI) model to strategize their network investment plans and to deploy their broadband services in their intended markets. The numbers of subscribers and average revenue per user (ARPU) are two dominant contributions to a good ROI. The rural areas are lacking both dominant factors and thus very often fall outside the radar of the Telco’s investment plans. The government agencies, therefore, shoulder the responsibility to provide broadband services in rural areas through the implementation of national broadband initiatives and regulated policies and funding for universal service provision. In this paper, we will outline a machine-learning technique which the Telco can use to plan for broadband investments in urban areas and beyond. The proposed technique predicts the socioeconomic potential of a geographical area in correspondence to its local characteristics. This technique is an empirical model that produces a correlation coefficient to quantify the statistical relationships between two or more values of local characteristics and socioeconomic potential. The model can help Telcos to prioritize their investments in urban and rural areas with higher potential for socioeconomic growth. By using this technique as a policy tool, Telcos will be able to prioritize areas where broadband infrastructure can be implemented using a government-industry partnership approach. Both public and private parties can share the initial cost and collect future revenues appropriately as the socioeconomic correlation coefficient improves. The proposed technique functions to formulate an empirical model using a curve-fitting software and to generate sufficient data using Genetic Algorithm to train a Support Vector Machine