Analisis Prediksi Profil Pelanggan Seluler Untuk Pemasaran Aplikasi Netflix

Abstract

Abstract The development of Indonesia ICT environment has made mobile video-on-demand (VOD) platform as one of emerging lifestyle. With advance smartphone technology, mobile phone subscribers able to enjoy high resolution mobile VOD service with greater user experience. The purpose of this study is to profile and predict potential customer of one of VOD platform, Netflix, for personalize marketing target. Using machine learning predictive analytic methodology, customer profile and behavior data is divided into 3 clusters using K-Means model before tested with several supervised model for getting best model for each cluster. Feature importance analysis will give marketing insight for product offering follows up to each targeted potential customer. Significant variables affecting Netflix buyer and non-buyer within 3 different clusters are defined clearly with number of potential customer that can be targeted as future subscriber of Netflix. Based on the research results, this method can be used by mobile operator to target potential customer with effective promotional or product offering by personalized marketing approach based on behavioral pattern and customer needs. It is expected by implementing this methodology, effectivity and accuracy of marketing will be increased compared to conventional method. Keywords: Predictive Analytic, behavior, Personalized Marketin