Build Your Own AI Investor: With Machine Learning and Python, Step by Step
| Size: | 20 MB (21021296 bytes) | Extension: |
| Author(s): Lee, Damon Publisher: www.valueinvestingai.com, Year: 2021 ISBN: 9781838132231 First EditionThis listing is for the First Edition. The Second Edition has been released, which longer, with improved clarity of code, formatting, text explanations as well as updating the AI picks for 2021 stock selection. This First Edition listing will be removed in due course. Build Your Own AI Investor
AI Investing
Do It All Yourself
Your AI Investor in action
Open source tools: All programming tools are available online for free. Working code from the book is available online for readers. Train your AI using free online historical stock market data. (For present day stock selection you will need a SimFin+ online subscription, no affiliation.) For beginners, exercises are provided in every chapter to develop your Python skills, slowly building competence until you can use Machine Learning tools for general problems.For advanced readers this books provides a good basis in value investing, framing the stock selection problem in a quantitative way, using Machine Learning algorithms on stock market data. |
| Table of contents: Preface About This Book Who Should Read This Book Book Roadmap Miscellaneous Chapter 1 – Introduction Investing in Stocks Formulaic Value Investing Value Investing with Machine Learning Machine Learning with Python Chapter 2 – Python Crash Course Background for Absolute Beginners Getting Python Python Coding with Jupyter Notebook Other Bits about Jupyter Notebook Basic Arithmetic Code Comments, Titles and Text Variable assignment Strings Python Lists Tuples Sets Custom Functions Logic and Loops Basic Loops Booleans Logic in Loops Python Dictionaries NumPy Discounted Cash Flows The Pandas Library Chapter 3 – Machine Learning Introduction with Scikit-learn What is Machine Learning? The Data Training the Models Machine Learning Basics with Classification Algorithms Decision Trees CART Algorithm Testing and Training sets Cross-Validation Measuring Success in Classification Hyperparameters, Underfitting and Overfitting Support Vector Machine Classification Regression Machine Learning Algorithms Linear Regression Linear Regression – Regularized Comparing Linear Models Decision Tree Regression Support Vector Machine Regression K Nearest Neighbors Regressor Ensemble Methods Gradient Boosted Decision Trees Feature Scaling and Machine Learning Pipelines Standard Scaler Power Transformers Scikit-Learn Pipelines Chapter 4 – Making the AI Investor Obtaining and Processing Fundamental Financial Stock data Getting Data and Initial Filtering Feature Engineering (and more filtering) Using Machine Learning to Predict Stock Performance Linear Regression Elastic-Net Regression K-Nearest Neighbors Support Vector Machine Regressor Decision Tree Regressor Random Forest Regressor Gradient Boosted Decision Tree Checking Our Regression Results So Far Chapter 5 – AI Backtesting Using an Example Regressor Building the First Bits Looping Through Each Year of a Backtest Backtest Data for an Individual Stock First Backtest Investigating Back Test Results Accounting for Chance of Default Chapter 6 – Backtesting – Statistical Likelihood of Returns Backtesting Loop Is the AI any good at picking stocks? AI Performance Projection Chapter 7 – AI Investor Stock Picks 2021 Getting the Data Together Making the AI Investor Pick Stocks Final Results, Stock Selection for 2021 Discussion of 2020 Performance |
Comments
Post a Comment