Directory Structure

Machine_Learning_Trading/
│
├── alpha_factors/ (Contains notebooks on feature engineering, TA-Lib, and Kalman filter)
│
├── data/ (Includes data files and notebooks for data creation and analysis)
│
├── decision trees/ (Notebooks related to decision tree models and their results)
│
├── deep_learning/ (Notebooks on deep learning models and PyTorch usage)
│
├── linear_models/ (Linear regression models and related notebooks)
│
├── machine_learning_process/ (Discusses machine learning workflow and concepts)
│
├── stock_selector/
│   ├── analyze_options.py (Python script for analyzing options)
│   ├── analyze_stock.py (Python script for stock analysis)
│   ├── black_scholes.py (Python script implementing the Black-Scholes model)
│   ├── brownian_motion.ipynb (Jupyter Notebook explaining Brownian motion)
│   ├── earnings_release.ipynb (Jupyter Notebook analyzing earnings releases)
│   ├── etf_analysis.ipynb (Jupyter Notebook for ETF analysis)
│   ├── futures.ipynb (Jupyter Notebook discussing futures trading)
│   ├── markovian_v_non-markovian.ipynb (Jupyter Notebook comparing Markovian and non-Markovian processes)
│   ├── scrape_url.py (Python script for scraping URLs)
│   ├── specific_stock_analysis.ipynb (Jupyter Notebook for analysis of specific stocks)
│   └── wiener_process.ipynb (Jupyter Notebook about the Wiener process)
│
├── time_series_models/ (Notebooks on time series analysis and models)
│
├── unsupervised_learning/ (Notebooks on PCA, dimensionality, and related topics)
│
├── results/ (Contains various result images and files)
│
└── README.md

/stock_selector/

Concomitant Focus Areas

• Practical Trading Algorithms: Linear regression, decision trees, and neural networks, tailored to predict market movements and analyze financial data.
• Time Series Analysis: Specialized notebooks on time series models such as ARIMA and GARCH provide insights into handling and forecasting sequential data, crucial for market trend analysis.
• Unsupervised Learning Techniques: Exploration of complex financial datasets with unsupervised learning methods like PCA, uncovering hidden structures and reducing dimensionality for better insights.
• Alpha Factor Research: Investigation of alpha factors and feature engineering to create predictive signals and enhance trading strategies.
• Real-World Data: Engagement with real-world datasets including stock prices, earnings releases, and economic indicators to practice and apply learned concepts.