Being able to predict the churn rate is the key to success for the telecommunication industry. It is also important for the telecommunication industry to obtain a high profit. Thus, the challenge is to predict the churn percentage of customers with higher accuracy without comprising the profit. In this study, various types of learning strategies are investigated to address this challenge and build a churn predication model. Ensemble learning techniques (Adaboost, random forest (RF), extreme randomized tree (ERT), xgboost (XGB), gradient boosting (GBM), and bagging and stacking), traditional classification techniques (logistic regression (LR), decision tree (DT), and k-nearest neighbor (kNN), and artificial neural network (ANN)), and the deep learning convolutional neural network (CNN) technique have been tested to select the best model for building a customer churn prediction model. The evaluation of the proposed models was conducted using two pubic datasets: Southeast Asian telecom industry, and American telecom market. On both of the datasets, CNN and ANN returned better results than the other techniques. The accuracy obtained on the first dataset using CNN was 99% and using ANN was 98%, and on the second dataset it was 98% and 99%, respectively.

Customization of products or services is a strategy that the business sector has embraced to build a better relationship with the customers to cater to their individual needs and thus providing them a fulfilling experience. This whole process is known as customer relationship management (CRM). In this context, we extensively surveyed 138 papers published between 1996 and 2021 in the area of analytical CRM. Although this study consisted of papers from different business sectors, a fair share of focus was directed to the telecommunication industry and generalized CRM techniques usages. Different science and engineering-based data repositories were studied to ascertain significant studies published in scientific journals, conferences, and articles. The research works on CRM were considered and separated into IT and non-IT-based techniques to study the methods used in different business sectors. The main target behind implementing CRM is for the better revenue growth of the company. Different IT and non-IT-based techniques are used in the analytical CRM area to achieve this target, and researchers have been actively involved in this domain. The purpose of the research was to show the impact of IT-based techniques in the business world. A detailed future course of research in this area was discussed.

The goal of data analytics is uncovering fruitful information and decision making from very large data sets in respect to various applications, which can redefine and improve customer relationships. With the increasing need of customizing every product and services the concept of Customer Relationship Management has been introduced. CRM is practiced in business by detecting patterns in customer data. Telecommunication sector is most well known and important to be dealing with customer interests than anyone else since they are well aware of their customers and can efficiently keep record of their customers’ actions. As the colossal volume of data produced by telecommunication companies cannot be evaluated manually, varied data analytics approaches are needed to be applied. Data analytics assists a business grasp its customers in a much superior way. In this paper we will make a survey on the concept of CRM and the use of data analytics in it.

The customers are the main entity of any business company and when it comes to telecommunication industry and its mature market, that number is too huge to be analyzed manually. That is where CRM analytics comes in the scenario, which helps in doing a better business. In this paper, we have analyzed a data-set of call records of 325 records, containing the attributes: directory number, called number, date, time, duration & units. Here we have used spectral clustering and k-means clustering to analyze the dataset to gain some information from the data to reach a certain conclusion. Considering this is a forward chaining research, there is no predefined target to be achieved. Here we have mainly done a comparative study between spectral clustering and k-means to see which one gives a better perspective of the data.