Predictive model for converting leads into repeat order customer using machine learning

In the competitive business landscape, customer relationship management (CRM) is pivotal for managing customer relationships. Lead generation and customer retention are critical aspects of CRM as they contribute to sustaining business growth and profitability. Also, identifying and converting leads into repeat customers is essential for optimizing revenue and minimizing promotional costs. This study focuses on developing a predictive model using machine learning techniques to convert leads into repeat order customers in conventional businesses. Leveraging data from a motorcycle distribution company in Jakarta and Tangerang, the study compares the performance of various models for predicting repeat orders. This includes individual models like DeepFM, random forest, and gradient boosting decision tree models. Additionally, it explores the effectiveness of stacking these models using logistic regression as a meta-learner. Furthermore, the study implements backward feature elimination for feature selection and hyperband for hyperparameter tuning to enhance model performance. The results indicate that Stacking model using base model default configuration stands out as the most robust, achieving the highest scores in accuracy (0.95), area under the curve receiver-operating characteristic curve (AUC-ROC) (0.67), log loss (0.19), weighted average precision (0.95), weighted average recall (0.95), and weighted average F1- score (0.92), effectively handling the imbalanced dataset.