Automatic Transactional Systems

obowiązkowe

The general aim of this course is to help students develop trading strategies using the

Python language. By the end of the course, students will:

● Understand the mechanics of quantitative trading in financial markets.

● Recognize the characteristics of financial data.

● Learn methods to evaluate trading strategies.

A specific objective is to provide a practical background for preparing advanced quantitative

trading strategies.

Lecture 1: Introduction to Continuous Double Auction Microstructure &

Python Assessment

Topics Covered

● Overview of financial markets and trading mechanisms

● Continuous Double Auction (CDA) microstructure

● Order types: market, limit, stop orders

● Order book dynamics and price formation

● Liquidity, depth, and market impact

● Role of market microstructure in trading strategy development

Activities

● Python proficiency test to assess readiness

● Discussion on how microstructure influences trading opportunities

Recommended Reading

1. Harris, L. Trading and Exchanges: Market Microstructure for Practitioners. (Chapters

1-3)

Lecture 2: Market Making Strategies with Constant Midprice

Topics Covered

● Fundamentals of market making and liquidity provision

● Implementing constant midprice strategies

● Setting symmetric bid and ask quotes

● Managing inventory risk

● Analysis of bid-ask spreads and profit calculation

Activities

● Coding a basic market-making algorithm in Python

● Simulating market scenarios with a constant midprice

Recommended Reading

2. Johnson, B. Algorithmic Trading and DMA: An Introduction to Direct Access Trading

Strategies. (Chapters 4-5)

Lecture 3: Dynamic Market Making with Variable Midprice

Topics Covered

● Adapting to changing market conditions and price volatility

● Strategies for updating quotes based on market signals

● Incorporating order flow information

● Adjusting for volatility and spread dynamics

● Advanced inventory and risk management techniques

Activities

● Enhancing the market-making algorithm to adjust to variable midprices

● Testing strategies on simulated data

Recommended Reading

2. Johnson, B. Algorithmic Trading and DMA: An Introduction to Direct Access Trading

Strategies. (Chapters 6-7)

Lecture 4: Pairs Trading and Statistical Arbitrage

Topics Covered

● Introduction to statistical arbitrage and mean-reversion

● Identifying cointegrated asset pairs

● Statistical tests for cointegration

● Spread computation and z-score analysis

● Execution of pairs trading strategies

Activities

● Data analysis to find suitable trading pairs

● Implementing a pairs trading algorithm in Python

Recommended Reading

3. Pole, A. Statistical Arbitrage: Algorithmic Trading Insights and Techniques. (Chapters 2-4)

Lecture 5: Arbitrage Opportunities in Financial Markets

Topics Covered

● Different forms of arbitrage: pure, risk, and statistical

● Spotting mispricings in related assets

● Execution challenges and transaction costs

Activities

● Case studies on historical arbitrage opportunities

● Simulating arbitrage strategies under different market conditions

Recommended Reading

4. Chan, E. P. Quantitative Trading: How to Build Your Own Algorithmic Trading Business.

(Chapters 5-6)

Lecture 6: Option Arbitrage Strategies

Topics Covered

● Fundamentals of options pricing

● Black-Scholes model and its assumptions

● The Greeks and their significance

● Identifying arbitrage opportunities in options markets

● Put-call parity violations

● Volatility arbitrage techniques

Activities

● Coding option pricing models in Python

● Developing algorithms for option arbitrage

Recommended Reading

5. Hull, J. C. Options, Futures, and Other Derivatives. (Chapters 9-11)

Lecture 7: Advanced Algorithmic Trading Techniques

Topics Covered

● Integrating multiple strategies for robust performance

● Optimization of algorithm parameters

● Introduction to machine learning in trading

● Supervised vs. unsupervised learning

● Overfitting and model validation

Activities

● Parameter tuning using cross-validation

● Exploring simple ML models for predictive analytics

Recommended Reading

6. López de Prado, M. Advances in Financial Machine Learning. (Chapters 1-3)

Lecture 8: Preparing for the Trading Competition

Topics Covered

● Overview of the simulated trading environment

● Competition rules and evaluation metrics

● Profitability, Sharpe ratio, drawdowns

● Best practices for developing robust trading algorithms

Activities

● Finalizing trading strategies

● Stress-testing algorithms under simulated conditions

Recommended Reading

7. Davey, K. Building Winning Algorithmic Trading Systems. (Chapters 7-8)

Lecture 9: Trading Competition Kick-Off

Activities

● Submission of trading scripts

● Live simulation begins, algorithms trade against each other

● Real-time monitoring and logging of performance

Objectives

● Apply theoretical knowledge in a practical setting

● Experience the dynamics of a competitive trading environment

Lecture 10: Results Analysis and Student Presentations

Activities

● Students present their trading strategies and results

● Explanation of the algorithm’s logic

● Performance metrics and outcome analysis

● Challenges faced and solutions implemented

● Peer feedback and discussion

Objectives

● Reflect on practical experiences

● Learn from diverse approaches and perspectives

Lecture 11: Advanced Topics in Trading Strategies

Topics Covered

● In-depth machine learning strategies

● Neural networks and deep learning applications

● Support vector machines for classification tasks

● Alternative data sources and their utilization

Activities

● Exploratory coding of ML models

● Discussion on future trends in algorithmic trading

Recommended Reading

6. López de Prado, M. Advances in Financial Machine Learning. (Chapters 5-7)

Lecture 12: Ethical and Regulatory Considerations

Topics Covered

● Regulatory environment for algorithmic trading (MiFID II, SEC rules, etc.)

● Ethical implications of automated trading

● Market manipulation concerns

● Fairness and transparency

Activities

● Case studies on regulatory actions

● Debate on ethical dilemmas in high-frequency trading

Recommended Reading

8. Boatright, J. R. Ethics in Finance. (Chapters 5-7)

Lecture 13: Course Review and Future Directions

Activities

● Summarizing key learnings

● Feedback session on content and structure

● Guidance on pursuing careers in algorithmic trading

Objectives

● Consolidate knowledge acquired

● Provide resources for continued learning

Harris, L. Trading and Exchanges: Market Microstructure for Practitioners.

2. Johnson, B. Algorithmic Trading and DMA: An Introduction to Direct Access Trading

Strategies.

3. Pole, A. Statistical Arbitrage: Algorithmic Trading Insights and Techniques.

4. Chan, E. P. Quantitative Trading: How to Build Your Own Algorithmic Trading

Business.

5. Hull, J. C. Options, Futures, and Other Derivatives.

6. López de Prado, M. Advances in Financial Machine Learning.

7. Davey, K. Building Winning Algorithmic Trading Systems.

8. Boatright, J. R. Ethics in Finance.

Knowledge

● Understands the fundamentals of Python programming.

● Knows how to use Python packages to prepare and analyze data to solve financial

problems and build trading strategies.

Skills

● Can set up a Python programming environment and install the required packages.

● Can implement investment strategies in Python.

Social Competence

● Recognizes that expert use of Python requires continuous practice and skill

development.

● Acquires the ability to seek and update knowledge in response to continually evolving

Python libraries.

(KW01, KW02, KU01, KU02)

1. Article Review: Unscored, but required to pass.

2. Python Script Submissions: 15 points

3. Final Test: 40 points (students must score ≥ 20 points to pass the course)

4. Project: 45 points

5. Activity: Up to 7 extra points

Total Score = (Article Review + Short tests + Final Test + Project + Activity) / 100

Attendance:

● Attendance is mandatory.

● Four or more unjustified absences result in course failure.

Class Attendance Registration:

● Students register their attendance by signing the attendance list.

● Mandatory short tests are also submitted at this time.

4. Grading Scale

Grade Total Score

%

Description

5 > 90% Very good

4+ > 80% Better than good

4 > 70% Good

3+ > 60% Satisfactory

3 > 50% Sufficient

2 < 50% Fail (total < 50% or final test < 50% or missed more than 4

classes)