Advances in Momentum Trading Strategies
What you'll learn
Requirements
Python Proficiency: Comfort with Python programming is key, as it's our primary tool for analysis and strategy development.
Market Savvy: A solid understanding of financial markets and trading principles will help you navigate the course content more effectively.
Mathematical Fluency: A strong ability to read and understand mathematical equations is crucial for grasping advanced concepts.
Foundation in Math & Statistics: Robust skills in linear algebra and statistics are essential, as they form the backbone of our trading strategies.
Advances in Momentum Trading Strategies is a comprehensive and in-depth course designed for graduate-level students and seasoned professionals. This course offers a unique blend of theory, practical application, and cutting-edge research, enabling participants to master the intricacies of momentum trading across various market conditions.
Course Sections:
A Century of Evidence on Trend-Following Investing: Explore the historical performance and methodology of trend-following strategies over a century, including during crises and different economic environments.
Momentum Turning Points: Unravel the concept of turning points in momentum trading. Learn about dynamic versus static strategies, and the impact of noise and persistence on signal quality.
Trending Fast and Slow: Delve into the theory and application of varying speed (window periods) in trend analysis. Discover the role of risk management and the statistics of S&P 500 in momentum strategies.
Position Sizing: Volatility Targeting: Understand the impact of volatility targeting on position sizing across asset classes, and why this approach is effective.
Deep Momentum Networks (Time Series Momentum Strategies): Learn about enhancing time-series momentum strategies using deep neural networks, including the construction of trading signals and performance evaluation.
Advanced Deep Momentum Networks with Change Point Detection: Explore the integration of change point detection in deep momentum networks, examining methodology and results.
Cross-Sectional Momentum Strategies with Learning to Rank: Gain insights into building cross-sectional systematic strategies using Learning to Rank (LTR), including Python library implementation for LambdaMart.
Market Conditions that Favor Strategies: Analyze various investment strategies like carry, momentum, and value in different market conditions. Learn about signal and portfolio construction.
Enhancing Cross-Sectional Strategies by Context-Aware LTR with Self-Attention: Understand how to enhance ranking in cross-sectional momentum strategies using context-aware models and transformer architecture.
Why This Course?
Whether you're a graduate student specializing in financial engineering, machine learning, applied mathematics, or a professional quant trader or analyst, this course will elevate your understanding and application of momentum trading strategies. It's not just a course; it's an investment in your future in the dynamic world of trading.
Who this course is for:
This course is NOT for beginners! Its an advanced course aimed at graduate level students and industry professionals.
Ambitious Graduate Students: Particularly those in Machine Learning, Applied Mathematics, Financial Engineering, and Computer Science, looking for a challenge.
Aspiring Quant Traders and Analysts: If you're eager to craft your own momentum-based trading strategies, this course is your launchpad.
Experienced Traders: Enhance your skill set with in-depth knowledge of cross-sectional and time-series momentum strategies.
What you'll learn
- Master Momentum Profits: Explore a century of profitable trend-following strategies and their evolution.
- Unlock Momentum Turning Points: Learn to detect and profit from key market changes.
- Exploit different volatility regimes, to dynamically swap between fast and slow parameters, to increase profits and improve the sharpe ratio.
- Smart Position Sizing: Use Volatility Targeting to enhance Sharpe Ratio and returns across assets.
- Learn how natural language processing (NLP) is used on news sources to construct sentiment signals and how to build time series momentum strategies.
- Deep Momentum Strategies: Discover advanced time-series tactics using deep learning.
- Rank with Precision: Apply Learning to Rank algorithms for superior cross-sectional momentum strategies.
- Forecast with Insight: Integrate crucial features into ML models for more accurate market predictions.
Requirements
Python Proficiency: Comfort with Python programming is key, as it's our primary tool for analysis and strategy development.
Market Savvy: A solid understanding of financial markets and trading principles will help you navigate the course content more effectively.
Mathematical Fluency: A strong ability to read and understand mathematical equations is crucial for grasping advanced concepts.
Foundation in Math & Statistics: Robust skills in linear algebra and statistics are essential, as they form the backbone of our trading strategies.
Advances in Momentum Trading Strategies is a comprehensive and in-depth course designed for graduate-level students and seasoned professionals. This course offers a unique blend of theory, practical application, and cutting-edge research, enabling participants to master the intricacies of momentum trading across various market conditions.
Course Sections:
A Century of Evidence on Trend-Following Investing: Explore the historical performance and methodology of trend-following strategies over a century, including during crises and different economic environments.
Momentum Turning Points: Unravel the concept of turning points in momentum trading. Learn about dynamic versus static strategies, and the impact of noise and persistence on signal quality.
Trending Fast and Slow: Delve into the theory and application of varying speed (window periods) in trend analysis. Discover the role of risk management and the statistics of S&P 500 in momentum strategies.
Position Sizing: Volatility Targeting: Understand the impact of volatility targeting on position sizing across asset classes, and why this approach is effective.
Deep Momentum Networks (Time Series Momentum Strategies): Learn about enhancing time-series momentum strategies using deep neural networks, including the construction of trading signals and performance evaluation.
Advanced Deep Momentum Networks with Change Point Detection: Explore the integration of change point detection in deep momentum networks, examining methodology and results.
Cross-Sectional Momentum Strategies with Learning to Rank: Gain insights into building cross-sectional systematic strategies using Learning to Rank (LTR), including Python library implementation for LambdaMart.
Market Conditions that Favor Strategies: Analyze various investment strategies like carry, momentum, and value in different market conditions. Learn about signal and portfolio construction.
Enhancing Cross-Sectional Strategies by Context-Aware LTR with Self-Attention: Understand how to enhance ranking in cross-sectional momentum strategies using context-aware models and transformer architecture.
Why This Course?
Whether you're a graduate student specializing in financial engineering, machine learning, applied mathematics, or a professional quant trader or analyst, this course will elevate your understanding and application of momentum trading strategies. It's not just a course; it's an investment in your future in the dynamic world of trading.
Who this course is for:
This course is NOT for beginners! Its an advanced course aimed at graduate level students and industry professionals.
Ambitious Graduate Students: Particularly those in Machine Learning, Applied Mathematics, Financial Engineering, and Computer Science, looking for a challenge.
Aspiring Quant Traders and Analysts: If you're eager to craft your own momentum-based trading strategies, this course is your launchpad.
Experienced Traders: Enhance your skill set with in-depth knowledge of cross-sectional and time-series momentum strategies.