Customer churn from a telecommunications company

In this study, we addressed the problem of classifying customer churn in a telecommunications company. We conducted exploratory data analysis, identified relationships between various attributes and the target variable. Next, we built five machine learning models for classifying customer churn: logistic regression, k-nearest neighbor, random forest, support vector machine, and gradient boosting. For each model, we used GridSearchCV to find the best parameters through cross-validation. As a result, we found the optimal parameters for each model. Finally, we evaluated the performance of each model on a test set using precision, recall, accuracy, and ROC-AUC metrics. We presented graphs for each metric, which indicated that the gradient boosting model achieved the best overall performance. Thus, we obtained a model that can be used to predict customer churn in a telecommunications company.

analytical report for the HR department

Prepared an analytical report for the HR department. Based on the analysis, made recommendations to the HR department on the recruitment strategy, as well as on interaction with existing employees.

Analytical report on educational programs

Based on the available data, prepare an analytical report that will further help producers of educational programs to effectively build a strategy for modernizing and improving courses.