Customer churn prediction model: a case of the telecommunication market

Abstract

The telecommunications market is well developed but is characterized by oversaturation and high levels of competition. Based on this, the urgent problem is to retain customers and predict the outflow of customer base by switching subscribers to the services of competitors. Data Science technologies and data mining methodology create significant opportunities for companies that implement data analysis and modeling for development of customer churn prediction models. The research goals are to compare different approaches and methods for customer churn prediction and construct different Data Science models to classify customers according to the probability of their churn from the company’s client base and predict potential customers who could stop to use the company’s services. On the example of one of the leading Ukrainian telecommunication companies, the article presents the results of different classification models, such as C5.0, KNN, Neural Net, Ensemble, Random Tree, Neural Net Ensemble, etc. All models are prepared in IBM SPSS Modeler and have a high level of quality (the overall accuracy and AUC ROC are more than 90%). So, the research proves the possibility and feasibility of using models in the further classification of customers to predict customer loyalty to the company and minimize consumer’s churn. The key factors influencing the customer churn are identified and form a basis for future prediction of customer outflow and optimization of company’s services. Implementation of customer churn prediction models will help to maintain customer loyalty, reduce customer outflow and increase business results

A novel artificial intelligent-based approach for real time prediction of telecom customer’s coming interaction

“…They concluded that ensemble way achieves much better results compared to using single classifier. A different example from industry is the recent work done by Fareniuk et al [11]. The author used LSTM to predict the next steps for current customers, assigning a probability to each step that would predict which helps in expecting customer churn and consequently prevent it.…”

“…The author used LSTM to predict the next steps for current customers, assigning a probability to each step that would predict which helps in expecting customer churn and consequently prevent it. Fareniuk et al [11] is 2022 used different data science and machine elarning models like k-nearest neighbor (KNN), NNs, and RF to classify the customers to loyal and likely to be churn for telecom companies using Ukrainian telecom company dataset and they achieved classification accuracy rate of 90%. Nguyen et al [12] in the same year, used the kernel SVM to predict customer's churn for telecom companies and they achieved a classification accuracy rate of 98.9%.…”

Application of a Data Mining Model to Predict Customer Defection. Case of a Telecommunications Company in Peru

“…For the development of the present research, the results of related works were reviewed in order to identify the relevant methodology for this type of casuistry, being CRISP-DM, the one that not only raises in one of its phases the procedure for the prediction model, but also evaluates the business context, as highlighted by (Fareniuk, Y., 2022), as well as the importance of the deployment of an interface that allows, with a simple language, to present the scenarios, so that the user can define a correct strategy for customer retention, as stated in .…”

Identifying Key Learning Algorithm Parameter of Forward Feature Selection to Integrate with Ensemble Learning for Customer Churn Prediction

“…In return, over a specific time span, a company faces a huge loss of its fan followings [6]. Because it is much more expensive to attract more customers than retain loyal customers [7]. The strategy of loyal customer retention plays a vital role in a company's growth.…”