Machine Learning with Azure Databricks for Finance Training Course

Introduction to Machine Learning in Financial Services

• Survey of prevalent machine learning applications in finance
• Advantages and complexities of machine learning in highly regulated industries
• Overview of the Azure Databricks ecosystem

Preparing Financial Data for Machine Learning

• Data ingestion from Azure Data Lake or database sources
• Processes for data cleansing, feature engineering, and transformation
• Conducting exploratory data analysis (EDA) within notebooks

Model Training and Evaluation

• Data partitioning and selection of suitable machine learning algorithms
• Training regression and classification models
• Assessing model performance using financial-specific metrics

Managing Models with MLflow

• Tracking experiments through parameter and metric logging
• Model storage, registration, and version control
• Ensuring reproducibility and comparing model outcomes

Deployment and Serving of Machine Learning Models

• Packaging models for batch or real-time inference capabilities
• Serving models via REST APIs or Azure ML endpoints
• Embedding predictions into financial dashboards or alert systems

Pipeline Monitoring and Retraining

• Scheduling regular model retraining with updated data
• Monitoring for data drift and maintaining model accuracy
• Automating end-to-end workflows utilizing Databricks Jobs

Case Study: Financial Risk Scoring

• Constructing a risk scoring model for loan or credit applications
• Explaining predictions to ensure transparency and regulatory compliance
• Deploying and testing the model in a controlled environment