EPAT Faculty > Dr. Ernest P. Chan
Dr. Ernest P. Chan
Founder of PredictNow.ai
About the Faculty
Dr. Ernest P. Chan is a recognized expert in applying statistical models and machine learning to finance. He is the Founder and Chief Scientist at PredictNow.ai, where he helps investors make informed decisions using advanced data-driven insights. Additionally, he is the Founder and Non-executive Chairman of QTS Capital Management, LLC, which focuses on systematic trading strategies. Dr. Chan has worked at notable organizations like IBM Research, Morgan Stanley, and Credit Suisse, gaining experience in pattern recognition, data mining, and quantitative trading.
Dr. Chan obtained his PhD in Physics from Cornell University and his B.Sc. in Physics from the University of Toronto. He has also authored several influential books, including Quantitative Trading and Algorithmic Trading. He was an Adjunct Associate Professor of Finance at Nanyang Technological University in Singapore and an adjunct faculty at Northwestern University’s Masters in Data Science program.
Dr. Chan combines extensive industry experience with deep technical knowledge, making him an excellent resource for understanding how to apply machine learning to trading effectively.
EPAT Teaching
Dr. Chan’s lecture focuses on understanding and applying momentum strategies using MATLAB. It covers why momentum happens, like slow news reactions or fund-driven market moves, and explains key concepts like roll returns (backwardation/contango) and time-series vs. cross-sectional momentum. You'll see real examples of futures and stock strategies, learn about momentum crashes, and explore how momentum strategies compare to mean reversion strategies, including their pros, cons, and exit approaches.
Quantra Courses
Trading in Milliseconds: MFT Strategies & Setup
This course covers Medium Frequency Trading (MFT), focusing on market microstructure, order flow analysis, and various order types. It includes topics like HFT gaming, spoofing, backtesting strategies, and executing trades with historical tick data.
Mean Reversion Strategies In Python
Learn to identify trading opportunities using statistical concepts like the ADF test and cointegration. You'll explore strategies such as pairs trading, index arbitrage, and long-short portfolios, along with live trading applications and risk management techniques.
Data & Feature Engineering for Trading
Build robust machine learning strategies for real-world trading by addressing key data-cleaning challenges in financial datasets. Learn to handle issues like survivorship bias, outliers, and structural breaks while applying techniques to improve strategy performance.
Implement neural networks and deep learning techniques, such as LSTM and RNN, in financial markets. Learn the applications and challenges of live trading, and gain hands-on experience with advanced trading strategies using deep learning models.
Trading Using LLM: Concepts and Strategies
Explore using Large Language Models (LLMs) to develop sentiment-driven trading strategies. The course covers LLM basics, prompt engineering, and practical applications such as sentiment analysis of FOMC transcripts and earnings calls, alongside rigorous strategy performance analysis.
This course teaches AI techniques to predict market trends using decision trees and ensemble methods. You'll explore classification and regression models, cross-validation, and hyperparameter tuning, with practical applications in live trading and optimizing AI models for performance.
Webinars Conducted
Trading Using LLM - Generative AI & Sentiment Analysis for Finance
2024
Trading in the Age of AI: How to Stay Ahead! | AI-Powered Trading Workshop 2024 [Panel Discussion]
2024
Introduction to Medium-Frequency Trading: Trading in Milliseconds
2023
How to Become a Successful Quant [Q&A Session]
2021
The Rewards and Perils of Mean Reversion Trading - "Lessons from our fund"
2020
Machine Learning In Trading - Q&A Session
2019
