Welcome to my portfolio! This repository showcases a variety of quantitative research projects, including time series forecasting, Monte Carlo simulations, data analysis with Python, and energy efficiency modeling.
I'm a scientist and data analyst with a background in nuclear physics, mathematical modeling, and statistical analysis. My expertise lies in data-driven problem solving, regression modeling, and time series forecasting. I have a strong foundation in Python, curve fitting, and energy analytics.
Previously worked in nuclear physics, where I developed mathematical models for deep inelastic scattering experiments at JLab and applied statistical fitting techniques to analyze experimental data.
Exploring applications of data science and forecasting in energy and financial markets, including power grid load forecasting and ARIMA-based financial modeling.
Programming: Python (pandas, numpy, scipy, matplotlib, scikit-learn, tensorflow)
Data Analysis & Modeling: curve fitting, regression analysis, statistical inference, time series forecasting
Applications: energy analytics, financial modeling, predictive analytics, feature engineering
- Expanding my portfolio with projects in forecasting, regression modeling, and energy analytics
- Transitioning into a research-focused or data-driven role in energy, R&D, or predictive analytics
If you're interested in data science, physics applications, or energy analytics, feel free to reach out!
Description: This project uses the SP500 index to predict future stock prices using ARIMA models based on historical data.
Objective: Forecast stock prices and evaluate model performance.
Description: Demonstrates Monte Carlo methods for estimating π, the volume of n-dimensional hyperspheres and analyzing Poisson and Gaussian distributions.
Technologies Used: Python (NumPy, Matplotlib), Monte Carlo methods (Acceptance/Rejection, Box-Muller Transformations)
Description: Analyzes polarization data to forecast unseen data points using statistical models.
Objective: Improve predictions from limited measurements by extrapolating data.
Description: Modeling and forecasting energy consumption trends using statistical analysis to improve energy grid efficiency.
Technologies Used: Python (NumPy, Pandas, NetworkX, Matplotlib, Scikit-Learn, pmdarima), Time Series Forecasting and Data Analysis, Energy Analysis
- Data Analysis & Forecasting: Utilizing time-series analysis to model and predict power demand using ARIMA, applying machine learning techniques such as K-means clustering to assess grid stability.
- Machine Learning: Implementing K-means clustering for stability classification, forecasting power demand using ARIMA, and leveraging regression models to understand energy efficiency in buildings.
- Statistical Analysis: Conducting load fluctuation analysis and calculating voltage deviations to detect instability in power grids, applying statistical methods to assess the stability of substations.
- Data Visualization: Creating visualizations using Matplotlib to showcase power demand trends, load fluctuations, and clustering results, as well as visualizing network graphs with NetworkX for grid structure representation.
- Energy & Power Systems: Simulating and analyzing power grid systems, from basic grid structures with substations and transmission lines to advanced stability analysis using demand simulations.
- Forecasting & Optimization: Using ARIMA models for forecasting future energy demand, and implementing strategies to balance grid loads for optimal efficiency.
- Programming: Proficient in Python, using libraries such as NumPy, Pandas, Scikit-Learn, and pmdarima for data processing, modeling, and machine learning tasks.