Artificial Intelligence in Finance
Since the work of Nobel Laureates Scholes, Markowitz, Sharpe, Merton and many others, quantitative methods have been established as a fundamental necessity in many branches of the financial sector.
The technology revolution has contributed to modernize que quantitative methods developed decades ago to take into account enhanced algorithms but most importantly, the use of rich data sets.
This course highlights, in a practical setting, how elements of artificial intelligence can be used to enhance our quantitative knowledge of finance, and when those methods do not work… yet.
| Lecture | AI Content | Finance | |
|---|---|---|---|
| 1 | Overview | Introduction |
We will start with one investment example and review how AI could assist in the different parts of the investment process |
| 2 | Data Analysis | Portfolio Theory |
Statistics builds the portfolio theory of the 1950’s; with powerful data science techniques, we can obtain enhanced results. We will discuss the example of financial crises |
| 3 | Trend Analysis | Revenue Projections |
Non-standard data sets, not based on accounting information, can be useful to predict accounting information, and stock performance. |
| 4 | Random Forests | Investing |
Derivatives are based on dependence structures, which model relationships. Random forests give us a powerful way to calculate them |
| 5 | Neural Networks | Risk & return |
It is often believed that AI can be used to predict the stock market behaviour. We will see what neural networks are and how they can be employed and why they don’t usually work for prediction of stock performance. We will, however, provide some objectives which can be achieved with neural networks. |
| 6 | NLP | ESG |
Modern decisions are taken with information which is derived from word databases, not just numbers. ESG is an example, and is based on the 17 sustainability goals of the United Nations |