Towards real-time customer experience prediction for telecommunication operators

Abstract

Telecommunications operators (telcos) traditional sources of income, voice and SMS, are shrinking due to customers using over-the-top (OTT) applications such as WhatsApp or Viber. In this challenging environment it is critical for telcos to maintain or grow their market share, by providing users with as good an experience as possible on their network. But the task of extracting customer insights from the vast amounts of data collected by telcos is growing in complexity and scale everey day. How can we measure and predict the quality of a user's experience on a telco network in real-time? That is the problem that we address in this paper. We present an approach to capture, in (near) real-time, the mobile customer experience in order to assess which conditions lead the user to place a call to a telco's customer care center. To this end, we follow a supervised learning approach for prediction and train our Restricted Random Forest model using, as a proxy for bad experience, the observed customer transactions in the telco data feed before the user places a call to a customer care center. We evaluate our approach using a rich dataset provided by a major African telecommunication's company and a novel big data architecture for both the training and scoring of predictive models. Our empirical study shows our solution to be effective at predicting user experience by inferring if a customer will place a call based on his current context.These promising results open new possibilities for improved customer service, which will help telcos to reduce churn rates and improve customer experience, both factors that directly impact their revenue growth.

Enhanced Churn Prediction in theTelecommunication Industry

“…In [18] study the quality of service is highly significant in tandem with, customer satisfaction, possession of superior technology, and cost of change and advertising. Difference between this findings and other like [16] [5] [16] [21] [20] on logistic regression may be attributable to the rigor on data selection and cleaning as well as the number of classification employed. The study of [23] that adopted the use of data mining tools to select and classify features within the selected customer churn dataset pointed out that Logistic Model is the best method due to its accuracy using neutral network, while this however, do not reflect the outcome of this study and differs from [32] that study showed that the different data mining techniques improve the prediction accuracy of the models because of the combined advantages of the components.…”

WhatsApp, Viber and Telegram which is Best for Instant Messaging?

“…end-to-end, which means that not even WhatsApp can read our messages [12,16,35]. Following WhatsApp's move to adding end-to-end encryption to its platform, on April 19, 2016 Viber implemented end-to-end encryption for all messages and [3,12,18], while Telegram uses a symmetrical encryption scheme called MTProto. The protocol was developed by Nikolai Durov and is based on 256-bit symmetric AES encryption, RSA 2048 encryption and Diffie-Hellman key exchange.…”

WhatsApp, Viber and Telegram which is Best for Instant Messaging?

“…Viber also offers two modes of voice quality: the normal and HD modes, with the latter very beneficial on high bandwidth networks. Perhaps the most unique feature is the Viber Out, which make it possible to Viber users to be in contact with people who are not on the service [3,17,18]. …”