ABHINAV SHAH

This course introduced me to the intersection of finance, risk management, and artificial intelligence, providing both theoretical foundations and hands-on applications. Over ten weeks, I  gained a comprehensive understanding of financial instruments, portfolio construction, risk modeling, and the latest AI-driven approaches to market analysis and trading strategies.

The course began with core financial instruments—stocks, bonds, and derivatives—before moving into the principles of risk and reward, volatility, and risk-adjusted performance measures such as Value-at-Risk and the Sharpe Ratio. I then explored portfolio optimization through Modern Portfolio Theory, the Efficient Frontier, and the Capital Asset Pricing Model. Building on this, I studied Random Walk theory, Geometric Brownian Motion, and Monte Carlo simulations as tools for modeling uncertainty in asset prices.

The second half of the course emphasized risk management and advanced modeling. Topics included hedging techniques, exposure management, and graphical network approaches to covariance structures. I engaged with factor models such as CAPM and Fama-French frameworks, extending to macroeconomic, fundamental, and statistical drivers of returns. Universe selection, clustering, and dimensionality reduction techniques (including Ridge, LASSO, and PCA) were introduced to address high-dimensional investment problems. Natural Language Processing (NLP) and sentiment analysis were applied to financial documents, demonstrating how unstructured text can inform investment signals. The course also highlighted real-world failures of quantitative finance and AI, such as Knight Capital’s algorithmic crash and the JPMorgan “London Whale” incident, underscoring the importance of robustness and risk controls.

The format combined weekly lectures, live coding sessions, and hands-on exercises. I worked in small groups to develop trading strategies that integrate AI and finance, culminating in a capstone project and final presentation. By the end of the course, I was able to:

• Analyze financial instruments and assess risk-return trade-offs.

• Apply optimization and simulation techniques to portfolio management.

• Use factor models, clustering, and machine learning tools for investment analysis.

• Incorporate NLP and sentiment analysis into financial forecasting.

• Critically evaluate both the potential and limitations of AI in financial markets.

This course helped me bridge finance and data science, preparing me to engage with the rapidly evolving landscape of quantitative investing and algorithmic trading.