Recommender System for Telecommunication Industries - Zambia Telecoms

RECOMMENDER SYSTEM FOR

TELECOMMUNICATION INDUSTRIES:

ZAMBIA TELECOMS

Mulizwa Soft, Mr David Zulu, Ruzive Mazhandu

University of Zambia, School of Natural Sciences , Computer Science department.

Abstract: Recommender systems use machine learning algorithms and artificial intelligence techniques to recommend products to customers, these algorithms use historical data of purchases of other people to determine which products to recommend to a particular customer, in general recommender systems are designed in such a way that they automatically generate personalized suggestions of products to customers. With the competitiveness that is growing in the Zambian telecom industry as a result of the new fourth mobile telecom service provider, telecommunication operators are looking for ways of attracting and keeping their subscribers on their network by giving affordable products to their subscribers, because they lack the ability to manage their customer retention rate, one of the main reason is that they do not have a personalized way of recommending products and services to their subscribers, as a result subscribers tend to migrate to new providers. This trend of subscribers migrating to new providers seeking for cheap affordable products proves to be a severe problem for Telecom providers as they experience subscriber base and revenue shrinkage. This research paper describes a Recommender System for Telecommunication companies using call detail reports (CDR’s), machine learning algorithms and big data concepts.

Keywords: Recommender systems, Telecom products/services, Machine learning algorithms, big data, Business Intelligence.

INTRODUCTION

Background information

• With increasing number of mobile telecommunications operators in Zambia, a customer is entitled with unlimited freedom to switch from one mobile operator to another if he is not satisfied with the services or pricing their providers are providing. This trend is not good for operators as they lose their revenue because of customers switching from one provider to another [1]

Statement of the problem

Telecommunication operators lack the ability to manage their customer retention rate because they do not have a personalized way of recommending products and services to their subscribers as a result subscribers tend to migrate to new providers. This trend of subscribers migrating to new providers proves to be a severe problem for Telecom providers as they experience subscriber base and revenue shrinkage, increasing churn rate causes a loss of future incomes [2].

Aim of the study

•Implement         a recommender        system for Telecommunications Company

Objectives    

• Study and examine the current existing recommender systems such as Netflix, Amazon, and EBay.
• Establish challenges telecommunication companies in Zambia face in terms of low revenue, churn, fraud etc. •        Determine how to process the raw call detail report file’s using the concept of big data.
• Design and implement a product recommender system which will recommend products that a subscriber is more likely to use. Research questions  
• How do we analyze the relationship between telecommunication subscribers and telecommunication products?
• What do the challenges telecommunication companies face that lead to high revenue loss, churn and bad customer experience?
• How do we process approximately five billion files/day?
• How best will Product recommender systems for mobile technology be utilized in order to assist solving the problem of low revenue, churn and fraud?

Significance of the study  

• Recommender based systems implemented using the concept of big data, machine learning or deep learning algorithms have a lot of advantages which will benefit telecommunication companies, for example better user experience, increased Traffic/Page Views, Increased Sales and improve customer retention.

 Related Works

• Recommender systems are the most successful implementation of web personalization and can be defined as personalized information filtering technology that is used to automatically predict and identify a set of interesting items on behalf of users according to their personal preferences. Recommender systems use the concept of rating to measure users’ preferences and a range of filtering techniques, and can be classified in multiple ways according to the nature of the input information. The content-based (CB) methods and collaborative filtering (CF) methods are the most popular techniques adopted in recommender systems. The CB methods recommend products by comparing the content or profile of the unknown products to those products that are preferred by the target user. However, these methods tend to rely heavily on textual descriptions of items, leading to several unsolved problems such as limited information retrieval, new user problems, and overspecialization [3]

METHODOLOGY

Introduction  

•Baseline study methodology and software design methodology Baseline study methodology  

The data dump or raw data will be collected from the CDR’s for the  

telecommunication company, SQL procedures will be used to collect the SQL dump or raw CDR’s will be processed using big data techniques, this data will be split into training set, test set and validation set

Software design methodology  

• Examine current recommender systems used by Amazon, EBay, Facebook, IMBD and Netflix or Coursera.
• Proposed recommender system for telecommunication companies
• Machine learning models or Algorithms

        • How do I know which model to choose for my problem?  

you first need to figure out whether your problem is linear or non-linear, if your problem is linear, you should go for Logistic Regression or SVM and If your problem is non-linear, you should go for K-NN, Naive Bayes, Decision Tree or Random Forest But from a business point of view, you would rather use, Logistic Regression or Naive Bayes when you want to rank your predictions by their probability. For example, if you want to rank your customers from the highest probability that they buy a certain product, to the lowest probability. Eventually that allows you to target your marketing campaigns. And of course, for this type of business problem, you should use Logistic Regression if your problem is linear, and Naive Bayes if your problem is non-linear.