Ermest P.Chan & Roger Hunter – Data & Feature Engineering for Trading

Description

Data & Feature Engineering for Trading will educate students on the significance of data engineering and feature engineering, which can be applied to both individual and institutional trading. The financial dataset must undergo preprocessing to be suitable for analysis. The predictive power of your algorithm is enhanced by extracting features from the datasets and setting the target variable for a specific machine learning problem.

Who is Ermest P.Chan & Roger Hunter?

Dr. Ernest P. Chan is the company’s founder. Since 1994, Ernie’s career has centered on the development of statistical models and sophisticated computer algorithms to identify patterns and trends in massive amounts of data. His machine learning expertise has been utilized by the Human Language Technologies group at IBM T.J. Watson Research Center, the Data Mining and Artificial Intelligence Group at Morgan Stanley, and the Horizon Trading Group at Credit Suisse. He is also the founder and managing member of QTS Capital Management, LLC, a quantitative investment management firm.

Dr. Roger Hunter is the scientific advisor for PredictNow.ai. Roger is an expert in the development of both high-performance automated execution systems and machine learning software. Roger was the founder and former manager of a highly profitable equity fund, as well as the founder and former CEO of a Thomson Reuters-acquired scientific software company. His company’s software is currently utilized by the Federal Reserve. Roger was a former mathematics professor at New Mexico State University and received his Ph.D. in mathematics from Australian National University. A profile of Roger was published in Bloomberg Businessweek.

Data & Feature Engineering for Trading with Ermest P.Chan & Roger Hunter

How often have you developed a profitable backtesting strategy that failed to generate profits in the real markets? A required course for developing machine learning strategies executable on trading platforms. This course focuses on the data cleansing of financial datasets using real-world examples.

• Section 1: Introduction to the Course
• Section 2: Challenges in Financial Data Engineering
• Section 3: Exploratory Data Analysis in Finance
• Section 4: Survivorship Bias for Stock Data
• Section 5: Redundant Stocks Data
• Section 6: Multiple Stock Classes: One or All?
• Section 7: Outliers-How to Identify and Deal With Them?
• Section 8: News Data-Numerical Features
• Section 9: News Data-Categorical Features
• Section 10: Structural Breaks in Financial Data
• Section 11: Fundamental Data-Merge Them Correctly
• Section 12: Look-ahead Bias-Deceptive Returns
• Section 13: Types of Bars-Features Extraction
• Section 14: Information Bars-Market Order Imbalances
• Section 15: Data Labelling for Better Outcomes
• Section 16: Why Stationary Features?
• Section 17 (Optional): Python Installation
• Section 18: Summary

AFTER THIS COURSE YOU’LL BE ABLE TO

Preprocess price data to resolve outliers, duplicate values, multiple stock classes, survivorship bias, and look-ahead bias issues.
Work with sentiment data to identify structural break and aggregate categorical features.
Examine fundamental data and resolve multiple data merging issues.
Create features and target variables for machine learning models.
Explain various challenges associated with the financial data

Refund is acceptable:

• Firstly, item is not as explained
• Secondly, Quantra – Data & Feature Engineering for Trading do not work the way it should.
• Thirdly, and most importantly, support extension can not be used.

Thank You For Choosing Us! We appreciate it.