Quant project

This project investigates the significant role of electrification in reducing global CO2 emissions, focusing on industries' contributions and the growing impact of electric vehicles (EVs). By integrating diverse data sources, including EIA reports, CO2 emissions data, and EV sales figures, the project employs advanced data analytics techniques like natural language processing (NLP) and machine learning to analyze trends and identify actionable insights. The findings aim to assess how electrification can drive the reduction of industrial emissions and contribute to global climate change mitigation efforts, providing valuable perspectives for policymakers and industry leaders.

In this project, I developed a robust pairs trading strategy focused on the Brent-WTI crude oil spread, leveraging mean-reversion principles and fundamental factors like the Baltic Dirty Tanker Index. By combining statistical arbitrage with transportation cost dynamics, I created a composite indicator to identify trade opportunities while managing risk through stop-loss mechanisms and transaction cost adjustments.

To objectively compare the fitness and improvement trajectories of two runners ("Hound" and "Collie") using their running data, addressing challenges of inconsistent data collection and differing training habits. Techniques & Methods: 1. Hypothesis Testing 2. Regression Modeling 3. Time-Series Analysis 4. Unsupervised learning (K-means clustering, Silhouette analysis for cluster validation) 5.

Analyst at an energy company considering a $2 billion investment in a new upgrader facility that would convert Cold Lake bitumen to Synthetic Crude. Tasks: 1. Data Analysis & Parameter Estimation 2. Simulate the spread using OUJ model 3. Develop a comprehensive NPV@Risk function with real option embeded 4. Risk-Reward Analysis (VaR, sensitivity analysis)