Predicting End-User Adoption to Mobile Services ()
ABSTRACT
It is no doubt that the sub-field of Artificial Intelligence, which uses the tenets of Machine learning and data mining has progressively gained popularity in the past years to become one of fundamental yet revolutionary technologies. It is the basis of systems that can learn and improve using algorithms and big data with minimal programming or none. It is envisaged that mobile computing will empower end-users to seamlessly access and consume digital content services regardless of spatial or temporal orientations. Such are already the features of smart phones that at production are bundled with trending and necessary services. Of the many capabilities that advancement in technology have actualized in smart devices, gaming, video streaming, online library access, and m-commerce access services are the commonly among smart device owners. Given the near-exponential growth in ownership of smart devices, there is a need to identify and prioritize mobile services, and such was focus of this study. In specific, the study used Decision Tree, a popular machine learning algorithm, to predict the adoption of mobile services among smart device owners. Besides this purpose, the study identified the core uses of smart phones, and data used in the study was from an open source and was retrieved from Pew Research Centre Internet and Technology website. The dataset had 140 variables and 2001 themes, from which only the key attributes were selected for analysis. The study established that the level of education was the significant predictor of the mobile phones usage while race of the user emerged as the least predictor of smart device usage. The findings indicated that smart mobile phones were mostly used for entertainment, getting locations, direction and for recommendation purposes.
Share and Cite:
Alloghani, M. (2018) Predicting End-User Adoption to Mobile Services.
Journal of Data Analysis and Information Processing,
6, 15-29. doi:
10.4236/jdaip.2018.62002.