Abstract: With the widespread popularity of the mobile Internet, the domestic online game market has become increasingly saturated. The cost of acquiring new users for game companies continues to increase. How to prevent the loss of existing users has become the focus of marketing. This paper predicts user churn based on a real game log data. First, user features are extracted and computed from log data. Second, a set of important features is selected by weight. Finally, a binary classification model is constructed with features as input and churn as output. 6 common algorithms such as random forest, support vector machine, multi-layer perceptron, gradient boosting decision tree, and logistic regression are comprehensively compared. The experimental results show that the random forest algorithm performs the best, and its model prediction accuracy reaches 91%.

Key words: churn prediction；Spark, binary classification, machine learning, random forest