Dive into the essence of machine learning, not through mere tool usage, but by unraveling its core principles via the lens of quantitative finance case studies. This course is meticulously crafted to establish a solid foundation in the theory and mathematical underpinnings of machine learning. With this theoretical groundwork in place, we then transition into a series of detailed research papers, each carefully selected to enrich your understanding and illustrate the practical applications of these concepts within the realm of quantitative finance.
The course is designed to first impart a solid understanding of the theory and mathematical foundations underpinning each section. Following this theoretical grounding, we delve into case studies and research papers to enrich your comprehension, illustrating the practical application of these concepts in quantitative finance.
This approach ensures a robust grasp of both the abstract and practical aspects of machine learning, providing you with a comprehensive insight into its deployment in the financial domain. Through detailed case studies, we’ll explore the nuances of algorithmic trading, risk management, asset pricing, and portfolio optimization, demonstrating how machine learning can uncover insights from vast datasets and drive decision-making.
This blend of theory, case study analysis, and interactive learning equips you with not just knowledge, but the confidence to apply machine learning innovations in quantitative finance.
Whether you’re a financial professional seeking to leverage machine learning for strategic decision-making, a mathematician curious about the financial applications of these algorithms, or someone entirely new to either field, this course is designed to equip you with the knowledge, skills, and insight to navigate and excel in the intersection of machine learning and finance.
-
2
Introduction to Machine LearningThis lecture will cover the essence of ML and its pivotal role in data analysis. We'll discuss various data types that fuel ML algorithms, delve into the core categories of ML (supervised, unsupervised, and reinforcement learning), and unravel the significance of correlation, regression, and cluster analysis in extracting meaningful insights from complex datasets.
-
3
Lecture 2: Data Handling and Preprocessing
The lecture will consider data cleaning, specifically the handling of missing values and the common functions to use in python for that. It will also examine Data Transformations such as common scaling methods. And finally will consider Data Reduction where we consider the tool of principal component analysis and how to visually understand the way in which it helps to reduce dimension.
-
4
Introduction to Machine Learning Quiz
-
5
Data handling and preprocessing Quiz
-
6
Case Study On Separating Noise from News
This lecture examines signal levels and the fact that "A strong signal emerges if weak signals are pointing in the same direction."
-
7
Assessment of Trading Signal Quality
This lecture considers both classification as well as regression metrics.
-
8
Generating Trading Signals by ML algorithms or time series ones?
This lecture examines time series analysis where we consider both stationarity and the importance when using ARIMA. It also examines how the random forest makes use of an ensemble approach to leverage the strength of each individual model to improve overall prediction accuracy and robustness against overfitting.
-
9
Generating Signals for Quant Models with Machine Learning
-
10
Introduction
We examine the general problem statement for portfolio optimization along with noise-induced instability.
-
11
Marcenko-Pastur
We investigate the Marcenko-Pastur probability density function as well as how it differs from that of the Ledoit-Wolf method.
-
12
De-Noising
We consider de-noising by identifying and adjusting noise-related eigenvalues.
-
13
NCO
This lecture examines Nested Cluster Optimization along with the difference between inter-clustering and intra-clustering.
-
14
Portfolio Optimization & NCO
Examine how to go about applying optimization methods including NCO.
-
15
Monte Carlo Simulations
After determining optimal allocations with NCO, Monte Carlo simulations can be used to test these allocations under varied market conditions.
-
16
Numerical Example
We examine how to analyze the performance of NCO on different types of portfolios (like minimum variance and maximum Sharpe ratio
-
17
Enhancing the MPT Efficient Frontier with Machine Learning
-
18
Introduction to Volume Prediction
This lecture will examine trading volume and why it is valuable in predicting future price movements.
-
19
Volume Prediction with Neural Networks
In this lecture we will consider the prediction of trading volume, especially the intraday change. This is a relatively underexplored area for financial forecasting.
-
20
Stock Trading Volume Prediction with Dual-Process Meta Learning
In this lecture we will examine how to go about using meta-learning to capture both common patterns and our stock-specific patterns.
In addition, we will consider how to employ an encoder-decoder framework to generate latent variables for better prediction.
-
21
Refining Equity Trading Volume Prediction with Deep Learning
-
22
Introduction to Sentiment Analysis
In this lecture we examine the intersection of technology and human emotion. We will investigate how algorithms can understand not just words, but the meaning behind them as well.
-
23
Harnessing News Sentiment
This lecture examines sentiment analysis. It specifically analyses how to go about making use of news sentiment specifically when dealing with foreign exchange futures strategies.
-
24
Bloomberg News Sentiment Case Study
This lecture examines a case study by Bloomberg news and social sentiment data.
-
25
Sentiment Analysis
-
26
Introduction to Satellite Images as Alternative Data
Consider a few applications with satellite imagery as alternative data.
-
27
Satellite imageries of container ports can predict world stock returns Part 1
Predicting Stock Market returns with satellite imagery.
-
28
Satellite imageries of container ports can predict world stock returns Part 2
Predicting Stock Market returns with satellite imagery part 2.
-
29
Satellite Images
-
30
Bayes Theorem
Examine how knowledge-driven AI and data-driven AI can be combined in decision-making.
-
31
Quant Research Pipeline
Investigate the traditional workflow.
-
32
Automated Pipeline
Understand the 3 modules found in the automated pipeline.
-
33
Factor Mining
Examine the factor mining pipeline.
-
34
Automated Modelling
Finding hyperparameters by use of search algorithms.
-
35
Model-Agnostic Explanation (1/2)
Understand the meaning of Individual Conditional Expectation (ICE) & Partial Dependence Plots (PDPs).
-
36
Model-Agnostic Explanation (2/2)
Examine LIME.
-
37
Explainable AI
Examine model explainability.
-
38
Knowledge- Driven AI
-
39
Automated, Explainable and Knowledge-driven AI
-
40
AI in Finance Introduction
This lecture examines the role of artificial intelligence in finance as well as alternative data.
-
41
Statistical arbitrage powered by Explainable Artificial Intelligence
This lecture examines how to apply ML and XAI (Explainable Artificial Intelligence) technologies to improve the financial performance of Statistical Arbitrage strategies.
-
42
Can AI Planning be used for Quantitative Finance Problems?
This lecture will examine multi-period asset allocation during different investment periods. It considers whether asset allocation problems can be represented using RDDL (Relational Dynamic Influence Diagram Language).
-
43
Leveraging AI
-
44
A Primer on Natural Language Processing for Finance
This lecture examines Natural Language Processing (NLP), a fusion of computer science and linguistics that utilizes algorithms to understand and interpret human language.
-
45
Earnings call and Big data in Investments
This lecture examines the structure of an earnings call. It will also examine the medium effect of big data. Note that page 46 of the paper can be considered for extra reading.
-
46
Generating Alpha using NLP Insights and ML - Part 1
This lecture examines the application of Natural Language Processing (NLP) and machine learning in enhancing investment strategies by analyzing conference call transcripts.
It will investigate different NLP classifiers, including the Loughran-McDonald sentiment dictionary, the FinBERT model, and Alexandria Technology’s ML Ensemble.
-
47
Generating Alpha Using NLP Insights and ML - Part 2
This lecture compares the three NLP Classifier strategies. It also considers breaking down returns in order to identify how much of the strategy's performance is due to these known risk factors and how much is unique or "alpha."
-
48
Dissecting Earnings Conference Calls with AI and Big Data
Lessons:
