<![CDATA[Shopee has evolved into one of the leading e-commerce platforms connecting sellers with consumers. However, the challenge of keeping users active and engaged on the platform has become increasingly complex. User retention, the ability of a platform to sustain and enhance user presence, is a key factor in the long-term success of an e-commerce platform. Understanding the factors influencing users' decisions to remain active or cease interactions with the platform involves analyzing various variables, including user behavior, preferences, shopping experiences, and interactions with the platform. This research is designed to develop an effective user retention prediction model using data from new Shopee users. By analyzing the data and applying machine learning techniques using Logistic Regression, Decision Tree, Gaussian Naive Bayes, Random Forest, KNN (K-Nearest Neighbors), MLP (Multi-Layer Perceptron), AdaBoost, and XGBoost methods, this study predicts user retention within a 14-day period after registration on Shopee. The results of this research indicate that the Random Forest model performs the best with an Accuracy value of 0.733677, Precision of 0.702161, Recall of 0.811626, and F1-Score of 0.752936. Cross-validation values demonstrate the model's consistency with an Accuracy of 0.727626, Precision of 0.698143, Recall of 0.801884, and F1-Score of 0.746328. The Random Forest model becomes a model with a high recall value, indicating good sensitivity in identifying users who retain. Consequently, the results of this research provide valuable insights for Shopee in developing retention strategies for new users, which is an important aspect in the growth and sustainability of the e-commerce business.]]>
Copyrights © 2024
