
Syllabus
- Provide a strong foundation in the tools and techniques used in algorithmic trading.
- Cover everything from basic programming concepts to advanced trading strategies and methods for research into new alpha sources.
- Apply everything in hands-on projects throughout the course.
1. Introduction
Trading Basics:
- Types of Trading
- Trading Strategies
- Introduction to Algorithmic Trading
Industry Overview:
- Industry Structure
- Size and growth
- The different sub-sectors
Approaches:
- Some simplified frameworks
- Full On Approaches
- Execution styles
Trading Platform Architecture:
- Data
- Features
- Models
Data:
- Market data sources – Aggregators and Exchanges.
- Scraped Data.
- Alternative Data sources.
2. Statistics and Time Series
ARIMA Models:
- Autoregressive, Moving Average Models and Integrated Models
- Detecting model types using Autocorrelation functions
- Solving Difference Equations
- Seasonality and State-Space ModelsTypes of stationarity and Brownian motion
Model Selection:
- Hypothesis Testing, Sequential Testing
- Covariance Penalties and Criteria
- Drop-out and Cross-Validation
- Sparsity, and Regularisation
Forecasting:
- Batch Updates
- Online Learning – Adaptive Filters – RLS and Kalman Filters
- GARCH
- Updating schemes and Stability
- Learning Rates and Cross Validation
Change-points and Regime Shifts:
- Change points vs Regime Shifts
- Endogenous Regimes / HMMs – EM method
- Regimes and weighted LS
- Chow, CUSUM and CUSUM-SQR tests
- Bayesian Changepoint Detection
- Breaks in Stationarity
- Changepoints and Stability
Multivariate Models:
- Causality – Granger and Otherwise
- Integration and Cointegration
- VAR / VARMA
- Exogenous restrictions / Conditional forecasting
3. Features and Factors
Feature Creation:
- Automating Features
- Feature Stores
- Best Practices from MLOps
Feature Selection:
- Feature Relevance – Sequential Filtering and Testing
- Feature Stability
- Examples : Lags, Movavs, etc
Exogenous Features:
- Economic Data
- Fundamental Data
- Releases and Surprises, Revisions and Corrections
- Changing the Frequency – Nowcasts and MIDAS
- Market Data
- Text and Sentiment
- Causality and Spillovers
Factor Investing: CAPM and APT
- Fama-French factors – Market, Value, Size
- Other Factors – Quality, Profitability, Leverage,
- Factor Proliferation and the Factor ZooAnomalies, Alpha and Time-Decay
- Risk Premia Investing
4. Trend Following
Momentum:
- Design
- Approaches and properties
- Impact on design
- Option value vs Reactivity
- Sharpe vs Skewness
- Continuous Time – Power Options and Trend
- Discrete time – skewness term-structure, autocorrelation and volatility
Nonlinear Momentum:
- Non-linear filter – Impact and benefits
- Risk and Return
- Returns distribution engineering, limitations and further direction
Momentum signals in practice:
- Time Series vs Cross- sectional Momentum
- Design Choices: MA, CMA, Z-scores, etc
- General Convolution Filters
- Technical indicators
- ARIMA models
Cross-Sectional Momentum:
- Relation with Time-series
- Fitting into APT/Fama-French
- Equities Quant (as a subsector) and Equities Factor Investing
- Turnover and Rebalancing Costs
- Mean-Reversion and Trend (and Mean-Reversion)
Momentum Breaking:
- Ultra Long-horizon
- Momentum breaking and Value
5. Carry and Volatility Strategies
Carry:
- Rationale – P vs Q Measures
- Definitions – Carry in Bonds, Futures, FX.
- Mathematical / Statistical Properties
- Negative Skewness Premium and Currency Crashes
- Diversification of Carry and Momentum
Mean-Reversion or pseudo market-making:
- Mean Reversion
- Rationales: Liquidity provision or Overreaction?
- Relation to other liquidity measures
- Stationary vs Non-Stationary processes
- Cointegration – Johansen, CCA and PCA
- Testing – Univariate and Multivariate Tests.
- Var-Ratio (Tests) vs Sharpe Ratio
- Shortcomings – Time-variation / Breaks
- “Optimal” MR TradingTiming
Relative Value Trading:
- RV in Delta-one space – Pairs, Spreads, Butterflies, Boxes and BasketsI(1) vs I(0): RV vs Trend
- Timing Entry points and mean reversion. Optimising
- Stationarity: Are RV trades stationary?
- Statistical arbitrage and Pairs Trading
Short-Gamma Trading:
- Variance risk premium
- Models of implied vol evolution and the risk/reward of short positions
- Expressions in different markets
- Hedging methods and new techniques
- Risk and signals
- Skewness and Scaling
6. Machine Learning and other New Techniques
Nonparametric Statistics
- Kernel Methods
- Empirical Densities and Bayesian Techniques
- Nonparametric Regression and Classification
Trees, Forests and Boosting
- Tuning the Parameters
- Feature Selection
- Boosting and Bagging
Neural Networks:
- Deep Neural Networks
- Recurrence and Memory
- Deep vs Wide – Efficiency and Stability
- Autoencoders
Reinforcement Learning:
- Decision Processes
- Stochastic Control
Genetic Algorithms:
- Genetic Representation, Fitness and Operators.
- Applications to Strategy Selection.
- Bandits and hyperparameter optimization.
7. Trading and Execution
Market Microstructure:
- Electronic vs Voice
- Limit Order Book
- RFQs vs Streaming Quotes
- Order types – Market, Limit, Spread, etc
- Other actions – Fills, Cancellation, etc
Execution Issues:
- VWAP and TWAP
- Auctions
- Transaction Costs
- Price Impact.
Optimising Execution:
- Stochastic Control
- Optimal market order placement
- Inventory constraints
- Extensions
- Optimal Market making and extensions
- Practical Implementation
- Fill probabilities
- Limit Order Book Simulations
- Reinforcement Learning
8. Backtesting and Performance Measurement
Performance:
- Sharpe & Sortino ratio etc.
- Distribution of Drawdowns.
- Impact of Leverage and Margining.
- Accounting for Funding and other Costs.
- Strengths and shortcomings of different approaches.
Back-testing, Simulations, and Hyper-parameter Tuning:
- Approaches to back-testing.
- Using Time Windows
- Training/Testing/Holdout Sets.
- Cross-validation.
- Possible biases.
Optimization:
- Classical Optimization
- Bayesian Optimization
- Bandits, Stopping Rules and Genetic algorithms.
- Multi-Objective Optimization.
- Off the shelf tools.
9. Allocation and Risk Management
Mean-variance optimization:
- Efficient Frontier.
- Allocation in Reality – Impact of volatility and Frictions.
- Quadratic Programming and Convex Optimization.
Constraints:
- Margin and Leverage.
- Funding
- Limits – Sector, sub-sector, strategy, name
Correlations:
- Approaches to Estimating the Correlation Matrix.
- PCA and Factor Analysis
- Dealing with Numerical Issues such as Sparseness.
- Shrinkage Methods.
Market & Liquidity Risk:
- Measuring Exposures to the Overall Market, Individual Sectors and Specific Factors.
- Correlation Estimation.
- Principal Component Analysis.
- Simulation and Stress Testing.
Credit Risk:
- Modelling Default Intensity and Recovery.
- Counterparty Credit Risk.
- Managing Credit Risk across the Firm.
Limits:
- Value at Risk and Expected Shortfall
- Setting Stop-Loss and other Limit Orders.
- Limits to Gross/Net Exposure to Rates/FX etc.
Operational & Legal/Regulatory Risk:
- Important to Capture as much as possible using Quantitative Techniques.
- Avoidance vs Mitigation.