franquant / a-quant-journey Goto Github PK

This repository contains the research and analysis presented by J. Francisco Salazar at the 1st Artificial Intelligence in Finance Conference (AIIFC), focused on leveraging machine learning and artificial intelligence to forecast asset returns.

This body of work delves into the robust application of quantitative methods in finance. The journey is illustrated through detailed a Jupyter Notebook that guide users from data acquisition to complex strategy backtesting, employing cutting-edge AI techniques for asset return forecasting.

Key Highlights:

• Data Exploration and Financial Time-Series Analysis
• Visualization of Financial Indicators
• Advanced Statistical Techniques
• Implementation of machine learning methods for unsupervised learning, like PCA, to isolate market return factors.
• Application of Machine Learning Models for Forecasting
• Algorithmic trading strategy backtesting using classifiers such as Naive Bayes, Logistic Regression, Decision Trees, Random Forest, SVM, and a Voting Classifier.
• Strategy Backtesting and Performance Metrics

• Presenter: J. Francisco Salazar
• Event: AI in Finance: Navigating the Future
• Date: April 26 - 27, 2024
• Location: Texas State University, San Marcos
• Hosted by: The Python Quants and the Department of Finance & Economics, McCoy College of Business, Texas State University

Clone this repository to peruse and interact with the financial analyses and models developed.

Ensure you have the necessary dependencies installed, including data manipulation, visualization, and machine learning libraries such as numpy, pandas, and scikit-learn.

We encourage contributions, questions, and feedback. Please feel free to reach out or contribute by opening an issue or submitting a pull request.

This project is open-sourced under the MIT License. See the LICENSE.md file for more details.

The content provided in this repository is for educational purposes only and is not intended as financial advice.