This repository contains applied Machine Learning projects focused on financial analysis and data-driven decision making.
Unsupervised learning project to analyze and segment S&P 500 stocks according to their financial behavior and risk profile.
Objective:
Identify which stocks are more suitable for investment depending on
the investor’s risk tolerance.
Techniques:
- PCA (dimensionality reduction)
- Exploratory Data Analysis
- Financial feature analysis
Supervised learning project using Random Forest to predict customer responses in a financial marketing context.
Techniques:
- Feature preprocessing
- Random Forest
- Model evaluation
- Python
- Pandas, NumPy
- Scikit-learn
- Matplotlib / Seaborn
- Jupyter Notebook
This project explores how Machine Learning can support investment decisions through risk-based analysis..
Alphatropy — where intelligence emerges from entropy.