Course Outline
Introduction
- Differentiating between statistical learning (statistical analysis) and machine learning
- Adoption of machine learning technology and talent by financial institutions for government applications
Understanding Different Types of Machine Learning
- Supervised learning versus unsupervised learning
- Iteration and evaluation processes
- Bias-variance trade-off considerations
- Combining supervised and unsupervised learning methods (semi-supervised learning)
Understanding Machine Learning Languages and Toolsets
- Open source versus proprietary systems and software for government use
- Python, R, and Matlab: comparing features and applications
- Libraries and frameworks for machine learning in a governmental context
Understanding Neural Networks
Understanding Basic Concepts in Finance
- Stocks trading fundamentals
- Time series data analysis
- Financial analyses techniques
Machine Learning Case Studies in Finance
- Signal generation and testing methodologies
- Feature engineering for financial datasets
- Artificial intelligence-driven algorithmic trading strategies
- Quantitative trade predictions using machine learning models
- Robo-advisors for portfolio management in the public sector
- Risk management and fraud detection techniques
- Insurance underwriting with advanced analytics
Hands-on: Python for Machine Learning
- Setting up a workspace for government applications
- Obtaining Python machine learning libraries and packages for government use
- Working with Pandas for data manipulation
- Using Scikit-Learn for machine learning tasks
Importing Financial Data into Python
- Utilizing Pandas for data import
- Integrating Quandl for financial datasets
- Connecting with Excel for data synchronization
Working with Time Series Data with Python
- Exploring and understanding time series data
- Visualizing time series data for analysis
Implementing Common Financial Analyses with Python
- Calculating returns on investments
- Applying moving window techniques
- Measuring volatility in financial markets
- Conducting ordinary least-squares regression (OLS)
Developing an Algorithmic Trading Strategy Using Supervised Machine Learning with Python
- Understanding the momentum trading strategy for government applications
- Exploring the reversion trading strategy in a public sector context
- Implementing a simple moving averages (SMA) trading strategy
Backtesting Your Machine Learning Trading Strategy
- Identifying common backtesting pitfalls for government use
- Components of an effective backtester for financial models
- Leveraging Python backtesting tools for accuracy
- Implementing a simple backtester in a governmental setting
Improving Your Machine Learning Trading Strategy
- Utilizing KMeans clustering techniques
- Applying K-Nearest Neighbors (KNN) for classification and prediction
- Implementing classification or regression trees for decision-making
- Employing genetic algorithms for optimization
- Managing multi-symbol portfolios effectively
- Incorporating a risk management framework in trading strategies
- Using event-driven backtesting methods
Evaluating Your Machine Learning Trading Strategy's Performance
- Utilizing the Sharpe Ratio for performance assessment
- Calculating maximum drawdown to assess risk
- Applying Compound Annual Growth Rate (CAGR) for long-term evaluation
- Measuring distribution of returns for comprehensive analysis
- Using trade-level metrics for detailed performance insights
- Summary of key findings and recommendations
Troubleshooting
Closing Remarks
Requirements
- Basic experience with Python programming for government applications
- Basic familiarity with statistics and linear algebra for government analysis
Testimonials (2)
the ML ecosystem not only MLFlow but Optuna, hyperops, docker , docker-compose
Guillaume GAUTIER - OLEA MEDICAL
Course - MLflow
I enjoyed participating in the Kubeflow training, which was held remotely. This training allowed me to consolidate my knowledge for AWS services, K8s, all the devOps tools around Kubeflow which are the necessary bases to properly tackle the subject. I wanted to thank Malawski Marcin for his patience and professionalism for training and advice on best practices. Malawski approaches the subject from different angles, different deployment tools Ansible, EKS kubectl, Terraform. Now I am definitely convinced that I am going into the right field of application.
