Machine-learning | Lead-Score Model

Implemented robust data cleaning and preprocessing techniques, ensuring high data quality and integrity. Addressed the issue of imbalanced data by applying advanced oversampling techniques like Synthetic Minority Over-sampling Technique (SMOTE). Employed a diverse range of machine learning models such as K-Nearest Neighbors (KNN), LightGBM, and Gradient Boosting to train and evaluate the data. Assessed overfitting concerns by utilizing learning curves, enabling accurate model selection. Leveraged the ROC AUC curve metric to evaluate and optimize model performance.