Machine Learning with Azure Databricks for Finance Training Cursus

Introduction to ML in Financial Services

• Overview of common financial ML use cases
• Benefits and challenges of ML in regulated industries
• Azure Databricks ecosystem overview

Preparing Financial Data for ML

• Ingesting data from Azure Data Lake or databases
• Data cleaning, feature engineering, and transformation
• Exploratory data analysis (EDA) in notebooks

Training and Evaluating ML Models

• Splitting data and selecting ML algorithms
• Training regression and classification models
• Evaluating model performance with financial metrics

Model Management with MLflow

• Tracking experiments with parameters and metrics
• Saving, registering, and versioning models
• Reproducibility and comparison of model results

Deploying and Serving ML Models

• Packaging models for batch or real-time inference
• Serving models via REST APIs or Azure ML endpoints
• Integrating predictions into finance dashboards or alerts

Monitoring and Retraining Pipelines

• Scheduling periodic model retraining with new data
• Monitoring data drift and model accuracy
• Automating end-to-end workflows with Databricks Jobs

Use Case Walkthrough: Financial Risk Scoring

• Building a risk score model for loan or credit applications
• Explaining predictions for transparency and compliance
• Deploying and testing the model in a controlled setting

Summary and Next Steps