Machine Learning with Azure Databricks for Finance Training Course

Foundations of ML in Financial Services

• A review of prevalent machine learning use cases in finance
• The advantages and complexities of ML adoption in regulated industries
• An overview of the Azure Databricks ecosystem

Preparation of Financial Data for ML

• Importing data from Azure Data Lake or relational databases
• Techniques for data cleaning, feature engineering, and transformation
• Conducting exploratory data analysis (EDA) within notebooks

Training and Assessing ML Models

• Data partitioning and the selection of appropriate ML algorithms
• Training regression and classification models
• Assessing model efficacy using finance-specific metrics

Managing Models with MLflow

• Monitoring experiments through parameters and key metrics
• Procedures for saving, registering, and versioning models
• Ensuring reproducibility and comparing model outcomes

Deployment and Serving of ML Models

• Preparation of models for batch or real-time inference
• Model serving via REST APIs or Azure ML endpoints
• Incorporating predictions into financial dashboards or alert systems

Monitoring and Retraining Pipelines

• Scheduling regular model retraining cycles with updated data
• Tracking data drift and monitoring model accuracy
• Automating comprehensive workflows using Databricks Jobs

Case Study: Financial Risk Scoring

• Development of a risk scoring model for loan or credit applications
• Methodologies for explaining predictions to ensure transparency and compliance
• Deployment and testing of the model within a controlled environment