Course Material - List of Books, Articles and Videos
Course 1: Financial Markets
M1 - Credit Risk and Financing
a. L1 - Saving and Borrowing
b. L2 - Counterparties and Credit Risk
c. L3 - Buying and Selling Short
d. L4 - Surveying the Financial Industry
M2 - Return and Volatility
a. L1 - Introducing Stocks and Cryptocurrencies
b. L2 - Types of Stocks and Cryptocurrencies
c. L3 - Measuring Performance of Stocks and Cryptocurrencies
d. L4 - Modelling Performance of Stocks and Cryptocurrencies
M3 - Correlation
a. L1 - Portfolio Returns and Standard Deviations
b. L2 - Correlation
c. L3 - Exchange Traded Funds
d. L4 - Volatility and Correlations
M4 - Leverage and Non-Linearity
a. L1 - Derivatives with an Emphasis on Options
b. L2 - Leverage and Non-Linearity
c. L3 - Home Equity as an Option
d. L4 - Option Strategies and Scenarios
M5 - Liquidity and Regulation
a. L1 - Securitization
b. L2 - Valuation Challenges: Market Frictions and Model Risk
c. L3 - Liquidity and the Credit Market
d. L4 - Leverage and Crisis
M6 - Model Failure and Crisis
a. L1 - The Balance Sheet: Leverage and Default
b. L2 - Debt and Equity: Financing Housing Development
c. L3 - The Housing Finance Problem and its Solution
d. L4 - More Than One Way to Pick a Stock
Course 2. Financial Data
Course 3. Financial Econometrics
M1: Getting Ready and Transformed for Financial Econometrics
M2: From Econometrics to ML
M3: Bivariate Dependence in Normal and Non-Normal Distributions
M4: Time Series Modelling I - ARMA
M5: Time Series Modelling II - GARCH
M6: Time Series Modelling III - Cointegration
M7: Top-down vs. bottom-up Agent-Based Simulations
Course 4. Derivative Pricing
M1: Pricing & Hedging Path Vanilla Options with The Binomial Tree
a. L1 - Financial Derivatives Basics
b. L2 - Option Pricing and Put Call Parity
c. L3 - Introducing Delta
d. L4 - Matching Volatility and Risk Measures
M2: Pricing & Hedging Path Dependent Options with The Binomial Tree
a. L1 - Intro to American Options
b. L2 - Dynamic Delta Hedging
c. L3 - Intro to Path Dependent Options
d. L4 - Intro to Monte Carlo Methods
M3: Market Completeness and The Trinomial Tree
M4: Black Scholes and Vasicek Models
M5: Black Scholes Limitations and Stylized Facts
M6: Pricing Options with Local Volatility and Stochastic Models
a. L1 - Implied Volatility and Volatility Smile
b. L2 - Local Volatility Models: Dupire
c. L3 - Local Volatility Models: CEV
d. L4 - Local Volatility Models CEV in Practice
M7: Pricing Options with Jump Diffusion Models
a. L1 - Stochastic Volatility: Heston
b. L2 - Option Pricing Under Heston (Monte Carlo)
c. L3 - Jump Diffusion Models
d. L4 - Merton Model
Course 5. Stochastic Modelling
M1 - Option Pricing Using Fourier Methods
a. L1 - Fourier Based Option Pricing
b. L2 - Characteristic Functions
c. L3 - Discrete Fourier Transform
d. L4 - Fourier Methods for Heston Model
M2 - Calibrating Merton and Heston Models
a. L1 - Merton Model Calibration
b. L2 - Combining Merton '93 and Heston '76
c. L3 - Bates (1996) in Practice
d. L4 - Calibrating the Bates
M3 - Calibrating CIR and BCC Models
a. L1 - Interest Rate Models
b. L2 - Calibrating CIR (1995)
c. L3 - BCC (1997) Model
d. L4 - BCC (1997) Model Calibration
M4 - Reinforcement Learning: Hidden Markov Models for Regime Changes
a. L1 - Reinforcement Learning - Intro to Markov Process
b. L2 - Markov Process - Further Applications
d. L4 - Regimes Changes and the EM Algorithm - An application to VIX
M5 - Reinforcement Learning: Dynamic Programming Applied to Optimal Selling
a. L1 - Reinforcement Learning - Introduction to Dynamic Programming
b. L2 - Dynamic Programming: The Q-Functionc. L3 - Dynamic Programming: Policy Iteration
d. L4 - Dynamic Programming: The Windy Gridworld, Async DP
M6 - Reinforcement Learning: Multi-Armed Bandits for Stock Selection
a. L1 - Reinforcement Learning - Multi-Armed Bandits
b. L2 - Multi-Armed Bandits: Stationary Casec. L3 - Multi-Armed Bandits: Non-Stationary Case
d. L4 - Multi-Armed Bandits: Improvements and Stock Picking Applications
M7 - Temporal Difference Methods Applied to Optimal Trading
a. L1 - Monte Carlo Methods
b. L2 - Temporal Difference Methodsc. L3 - Cliff Walk SARSA and Q-Learning
d. L4 - Optimal Trading Behavior
Project 1, Project 2, Project 3
Course 6. Machine Learning in Finance
M1: Introduction to Machine Learning: Supervised Learning
c. L3 - Supervised Models: Classification
d. L4 - Supervised Models: Classification Case Study
e. Project Work
M2: Introduction to Machine Learning: Unsupervised Learning
a. L1 - Unsupervised Machine Learning - Clustering
b. L2 - Hierarchical Clustering
c. L3 - Dimensionality Reduction - PCA
d. L4 - Principal Component Analysis and Interest Rate Modelling
M3: Classification Problems with Bayes Methods and Classification Trees
a. L1 - Bayesian Statistics in Classification
b. L2 - Bayesian Statistics in Practice
c. L3 - Trees
d. L4 - Trees in Practice
M4: Improving Trees Using Ensemble Learning
a. L1 - Ensemble Learning
b. L2 - Ensemble Learning in Practice
c. L3 - Boosting Methods
d. L4 - Ensemble Learning Comparisons
M5: Support Vector Machines and Neural Networks
a. L1 - Support Vector Machines
b. L2 - Support Vector Machines in Practice
c. L3 - Neural Networks
d. L4 - Neural Networks in Finance
M6: Going Deeper with Neural Networks
a. L1 - Introduction to Deep Learning
b. L2 - Application of Deep Learning in Predicting Yield Curves
c. L3 - Optimization
d. L4 - Credit Risk Modeling - Application of Deep Learning
M7: Hyperparameter Tuning and Model Optimization
b. L2 - House Prediction and Hyperparameter Tuning
d. L4 - Bitcoin Trading Strategy
M8: Introduction to Neural Networks
a. L1 - Introduction to Neural Networks - Quiz
b. L2 - Linear Models in TensorFlow - Timing Factors and Smart Beta Strategies
c. L3 - Multilayer Perceptrons
d. L4 - Multilayer Perceptrons - Timing Factors and Smart- Beta Strategies
Course 7. Deep Learning in Finance
M1: Financial Time-Series Predictability for Stock Timing with MLP
a. L1 - MLPs
b. L2 - MLP for Classification: Timing AAPL Stock
c. L3 - Encoding Time Series as Images
d. L4 - Deep CNNs: Implementing a Garmian Angular Field
M2: Convolutional Neural Networks for Pattern Recognition in Financial Markets
a. L1 - CNN: Introduction
b. L2 - CNNs: Candlesticks and Convolutions
c. L3 - Towards Modern CNNs
d. L4 - CNNs: Training a CNN
M3: Deep Convolutional Neural Networks for Financial Time Series
b. L2 - Transfer Learning for CNNs
c. L3 - Encoding Time Series as Images
d. L4 - Deep CNNs: Implementing a Garmian Angular Field
M4: Predicting Stock Prices Using Recurrent Neural Networks
a. L1 - Recurrent Neural Networks (RNNs)
b. L2 - RNN Implementation
c. L3 - Backpropagation in RNNs
d. L4 - Multivariate RNNs
M5: Stock Timing Strategies with Memory Under Modern Recurrent Neural Networks
a. L1 - GRUs and LSTMs
b. L2 - LSTMs for Predicting BTC Prices
c. L3 - Deep and Bidirectional LSTMs
d. L4 - Bidirectional LSTMs and BTC Prices
M6: The Cross-Section of Stock Returns and Optimal Portfolio Choices Using Autoencoders
b. L2 - Application of Auto Encoders
c. L3 - Further Auto Encoder Topics
d. L4 - Portfolio Choice with Sparse Auto Encoders
M7: Advanced Topics In Deep Learning For Finance
Course 8. Portfolio Management
M1: Value at Risk and Classical Portfolio Theory
c. L3 - From Utility Theory to Classical Port Theory
d. L4 - Math of Classical Port Theory
M2: Elements of Advanced Port Theory
b. L2 - Beyond Mean-Variance Optimization
c. L3 - Optimal Portfolio and Currency Management
M3: The Blackman-Litterman Model
b. L2 - Critical Line Algorithms & Corner Portfolios
c. L3 - Some Abuses of BL Model
d. L4 - PSO and Probabilistic Approaches
M4: Behav Finance & Application to Port Theory
b. L2 - Prospect Theory
c. L3 - Behavioral Portfolio Theory
M5: Kelly and Risk Parity - Optimizing for Growth and Risk
a. L1 - The Kelly Criterion and The Optimal Growth Strategy
b. L2 - The Kelly Criterion Evolves
c. L3 - Introducing Risk Parity
d. L4 - Machine Learning Extensions of Risk Parity
M6: Advances and Challenges in Factor Investing
a. L1 - Factor Investing - Profitable Anomalies or Anomalous Profits
b. L2 - Smart Beta, Herding and Not so Smart Beta
c. L3 - Factor Models with Machine Learning
d. L4 - Advanced Factor Construction
M7: Information Theory and Graphs for Improved Portfolios
a. L1 - Shrinking the Covariance Matrix
b. L2 - The Correlation Matrix Reloaded
c. L3 - Information and Distance
d. L4 - Hierarchical Risk Parity
M8: Better Backtesting and Reinforcement Learning
a. L1 - Backtesting without Overfitting: Deflating Sharpe and Overcoming Selection Biasb. L2 - Combinatorial Purged Cross-Validation
c. L3 - Reinforcement Learning for Portfolio Managementd. L4 - Reinforcement Learning in Real Life
Course 9. Risk Management
M1: Systemic Risk
a. L1- Systemic Risk: Macroeconomic Indicators
b. L2 - Systemic Risk: Networks and Principal Components
c. L3 - Systemic Risk: Conditional and Illiquidity Risk
d. L4 - Systemic Risk meets Machine Learning
M2: Modelling and Heding Variance
a. L1- Trading Volatility - Variance Swaps
b. L2 - Variance Swaps - Spanning with Options
c. L3 - Jumping for Better Volatility Estimation
d. L4 - Order Statistics Volatility Estimation in Action
M3: Estimating Tail Loss with Deep Learning
a. L1- DeepVar - Value at Risk meets Long Short Term Memory
b. L2 - DeepVar - The Python Implementation
c. L3 - Forecasting Volatility with Transformers
d. L4 - MultiLayer Transformers in Action
M4: Predicting Stock Prices Using Recurrent Neural Networks
a. L1- Risk Modelling with Extreme Value Theory
b. L2 - Block Maxima - Indonesian Gold
c. L3 - The Theorem and Politics of Extreme Values
d. L4 - Extreme innovations in VaR Modelling
M5: Bayesian Network for Risk Management
M6: Network Learning for Risk Management
M7: Climate Risk and Vasicek Model
M8: Dynamic Bayesian Network and Cohesive Risk Management
Course 10. Capstone
M0: Capstone Lecture Notes
c. L2 - Performance Chasers and Knife Catchers
d. L3 - The Theorem and Politics of Extreme Values
e. L4 - Extreme innovations in VaR Modelling
f. L5 - Seed Investors & Correlation Nuts
g. L6 - Market Myths - Owning Stocks & Ways to Trade
h. L7 - Turkeys and Nobel Laureates
i. L8 - Option Selling Strategies - Risk Protection
j. L9 - Market Myths - Holding positions over the weekend
m. L11 - Hidden Drawdown
o. L12 - Defense is the Best Offense
p. L13 - Data Mining Bias
q. L14 - Out of Sample Performance Deterioration
- Rebecca Lehman: Volatility
- Bruno Dupire: Volatility Trading
- Anca Dimitriu: Trading Psychology
- Irene Aldridge: Guest Lecture
M2: Capstone Project
a. Paper