FE670 Algorithmic Trading Strategies


Course Catalog Description

Introduction

This course investigates methods implemented in multiple quantitative trading strategies with emphasis on automated trading and quantitative finance-based approaches to enhance the tradedecision making mechanism. The course provides a comprehensive view of the algorithmic trading paradigm and some of the key quantitative finance foundations of these trading strategies. Topics explore markets, financial modeling and its pitfalls, factor model based strategies, portfolio optimization strategies, machine learning, and order execution strategies. The data mining and machine learning based trading strategies are introduced, and these strategies include, but not limited to, weak classifier method, boosting, random forest, deep neural network and genetic programming algorithmic emerging methods with multiple data sources. The trading strategy examples will be demonstrated in Python, and the course requires programming skills.

Prerequisite:

  • FE 570– Market Microstructure and Trading Strategies

Campus Fall Spring Summer
On Campus X
Web Campus

Instructors

Professor Email Office
Steve Yang
syang14@stevens.edu Babbio 536

More Information

Course Outcomes

After successful completion of this course, students will:

  • The students will learn the tools and common methodology used in research and devel-opment of quantitative trading strategies.
  • The process of finding new “alphas” will be illustrated using available datasets, the pro-jects will illustrate the details of “backtesting” and systematic portfolio construction.
  • Most common trading strategies will be discussed in detail, while the exercises and pro-jects will offer the creative opportunities to refine the models.
  • At the end of the course the students will be able to analyze and develop strategies inde-pendently, will develop the skills to build optimal portfolios, perform hedging and re-search new non-conventional ideas.

Course Resources

Textbooks

Raja Velu, Maxence Hardy, Daniel Nehren, Algorithmic Trading and Quantitative Strategies, Chapman and Hall/CRC Financial Mathematics Series, 1st Edition (2020) [Required]

Stefan Jansen, Machine Learning for Algorithmic Trading: Predictive models to extract signals, Packt Publishing, Ltd. 2nd Edition (2021) [Optional]

Frank J. Fabozzi, Sergio M. Focardi, and Petter N. Kolm, Quantitative Equity Investing: Techniques and Strategies (Wiley, 2010) [Optional]

Barry Johnson, Algorithmic Trading & DMA, 4Myeloma Press London, 2010 [Optional]


Grading

Grading Policies

Weights
1 Homework Assignment 40%
2 Midterm Exam 30%
3 Final Project 30%
4 Total Grade 100%

Lecture Outline

Topic Reading HW
Week 1 An Overview of Trading and Markets Velu, Hardy, Nehren [1],
Barry Johnson [1,2]
Week 2 Basic Models and Empirics Velu, Hardy, Nehren [2,3],
Jansen [2,3]
Week 3 Factor Models and Estimation Fabozzi, Focardi, Kolm [5],
Jansen [4]		 HW1
Week 4 Alpha Factor Trading Strategies Fabozzi, Focardi, Kolm [6-7],
Jansen [7]
Week 5 Mean Variance Portfolio Theory Fabozzi, Focardi, Kolm [8]
Jansen [5]
Week 6 Portfolio Theory Beyond Markowitz Fabozzi, Focardi, Kolm [9] HW 2
Week 7 Robust Portfolio Optimization Fabozzi, Focardi, Kolm [10] EXAM 1
Week 8 Statistical Arbitrage and Pair Trading Strategies Velu, Hardy, Nehren [4, 5]
Jansen [6]
Week 9 Machine Learning Trading Strategies: Random Forests, Ada Boosting, Gradient Boosting Research Papers,
Jansen [11, 12]
Week 10 Trading Strategies based on Alternative Data: Topic Model and Sentiment Analytics Research Papers,
Jansen[15, 16, 18, 19]		 HW 3
Week 11 Deep Learning Strategies: Autoencoder, GANs, and Reinforcement Learning Research Papers,
Jansen[20, 21, 22]
Week 12 Trade Execution & Market Impact Fabozzi, Focardi, Kolm [11],
Velu, Hardy, Nehren [8]		 Proposal
Week 13 Transaction Costs & Optimal Execution Strategies Barry Johnson [7, 8, 9],
Velu, Hardy, Nehren [9, 10]		 HW 4
Week 14 Enhancing Trading Strategies & Technology Considerations Barry Johnson [10],
Velu, Hardy, Nehren [11, 12]
Week 15 Final Project Presentation EXAM 2