Bank Marketing Prediction MLOps Pipeline Project
Text
ClassificationWorked on an end-to-end machine learning and MLOps project for bank marketing prediction using TensorFlow Extended (TFX) and Apache Airflow. The project involved preprocessing customer marketing data, validating datasets, training classification models, and evaluating model performance through automated ML pipelines. Performed data labeling, classification, data validation, and model evaluation tasks to improve prediction quality for customer subscription outcomes. Used preprocessing pipelines for feature transformation, handling missing values, encoding categorical variables, and scaling numerical features. Worked with TensorFlow Model Analysis (TFMA), TensorBoard, and Airflow DAGs to monitor pipeline execution, evaluate fairness metrics, and track model performance. Applied evaluation metrics including accuracy, precision, recall, F1-score, and AUC to compare models and improve deployment readiness.