Customer Churn in Retail E-Commerce Business: Spatial and Machine Learning Approach

This study is a comprehensive and modern approach to predict customer churn in the example of an e-commerce retail store operating in Brazil. Our approach consists of three stages in which we combine and use three different datasets: numerical data on orders, textual after-purchase reviews and socio-geo-demographic data from the census. At the pre-processing stage, we find topics from text reviews using Latent Dirichlet Allocation, Dirichlet Multinomial Mixture and Gibbs sampling. In the spatial analysis, we apply DBSCAN to get rural/urban locations and analyse neighbourhoods of customers located with zip codes. At the modelling stage, we apply machine learning extreme gradient boosting and logistic regression. The quality of models is verified with area-under-curve and lift metrics. Explainable artificial intelligence represented with a permutation-based variable importance and a partial dependence profile help to discover the determinants of churn. We show that customers’ propensity to churn depends on: (i) payment value for the first order, number of items bought and shipping cost; (ii) categories of the products bought; (iii) demographic environment of the customer; and (iv) customer location. At the same time, customers’ propensity to churn is not influenced by: (i) population density in the customer’s area and division into rural and urban areas; (ii) quantitative review of the first purchase; and (iii) qualitative review summarised as a topic.

Customer churn analysis using XGBoosted decision trees

Customer relationship management (CRM) is an important element in all forms of industry. This process involves ensuring that the customers of a business are satisfied with the product or services that they are paying for. Since most businesses collect and store large volumes of data about their customers; it is easy for the data analysts to use that data and perform predictive analysis. One aspect of this includes customer retention and customer churn. Customer churn is defined as the concept of understanding whether or not a customer of the company will stop using the product or service in future. In this paper a supervised machine learning algorithm has been implemented using Python to perform customer churn analysis on a given data-set of Telco, a mobile telecommunication company. This is achieved by building a decision tree model based on historical data provided by the company on the platform of Kaggle. This report also investigates the utility of extreme gradient boosting (XGBoost) library in the gradient boosting framework (XGB) of Python for its portable and flexible functionality which can be used to solve many data science related problems highly efficiently. The implementation result shows the accuracy is comparatively improved in XGBoost than other learning models.

Customer Decision Prediction Using Deep Neural Network on Telco Customer Churn Data

Customer churn is the most important problem in the business world, especially in the telecommunications industry, because it greatly influences company profits. Getting new customers for a company is much more difficult and expensive than retaining existing customers. Machine learning, part of data mining, is a sub-field of artificial intelligence widely used to make predictions, including predicting customer churn. Deep neural network (DNN) has been used for churn prediction, but selecting hyperparameters in modeling requires more time and effort, making the process more challenging for the researcher. Therefore, the purpose of this study is to propose a better architecture for the DNN algorithm by using a hard tuner to obtain more optimal hyperparameters. The tuning hyperparameter used is random search in determining the number of nodes in each hidden layer, dropout, and learning rate. In addition, this study also uses three variations of the number of hidden layers, two variations of the activation function, namely rectified linear unit (ReLu) and Sigmoid, then uses five variations of the optimizer (stochastic gradient descent (SGD), adaptive moment estimation (Adam), adaptive gradient algorithm (Adagrad), Adadelta, and root mean square propagation (RMSprop)). Experiments show that the DNN algorithm using hyperparameter tuning random search produces a performance value of 83.09 % accuracy using three hidden layers, the number of nodes in each hidden layer is [20, 35, 15], using the RMSprop optimizer, dropout 0.1, the learning rate is 0.01, with the fastest tuning time of 21 seconds. Better than modeling using k-nearest neighbor (K-NN), random forest (RF), and decision tree (DT) as comparison algorithms.

Predictions from an Empirical Study in the Turkish Mobile Telecommunications Market on the Determinants of Mobile Customer Churn

Acquiring new customers compared to holding the existing ones is costlier and more troublesome for businesses, so customer retention is of great importance in today's intensely competitive environment. It is crucial in customer relations management to identify and analyse customers whose loyalty decreases and who tend to leave, and prevent churn through various methods under resource constraints. This issue is especially prominent in the mobile communication market. This paper uses a binomial logit model based on a survey with 637 mobile users in Turkey to determine the factors affecting customer churn and how they find their effect. Results indicate that, among various factors, network quality, billing, tariff level, tariff plan, and education level are the determinants affecting customer churn and associated with the intention to switch. Our findings demonstrate implications for both managers and rule-makers in the mobile telecommunications sector.