I come from an engineering background with strong analytical foundations and hands-on problem-solving experience. My approach combines structured thinking, data-driven decision-making, and precision under pressure.
I’ve applied quantitative logic in both technology and financial domains — from algorithmic reasoning in programming to practical exposure with futures and options trading. I understand how theoretical models translate to real-world market behavior.
Currently, I’m sharpening my derivative and mathematical finance fundamentals while building projects that blend computation, finance, and automation. My goal is to leverage quantitative tools to solve real-market problems and scale intelligent systems.
June 2025 - December 2025
Worked on preprocessing and analyzing datasets, building and testing baseline ML models, and supporting internal workflows with structured documentation and reporting. Collaborated with the engineering team to run experiments, evaluate results, and refine data pipelines — strengthening my practical understanding of applied ML, data quality, and model performance fundamentals.
August 2025 - December 2026
Pursuing a rigorous quantitative curriculum covering financial mathematics, statistical modeling, derivatives pricing, risk management, and machine learning applications in finance. Selected for the Dean’s Scholarship and appointed as a Student Ambassador for the MQF program, supporting prospective students and representing the program at official events. Focused on developing strong quantitative and computational finance skills through advanced coursework and industry-aligned projects.
October 2020 - August 2024
Completed a rigorous engineering program with a specialization in data science, integrating mathematics, programming, and statistical analysis. Proactively applied computational methods to finance, building projects in insurance risk modeling, U.S. Treasury bond risk analysis, forex market prediction using machine learning, and multi-model backtesting. Developed strong skills in quantitative analysis, algorithmic modeling, and data-driven decision frameworks.
Jan 2024 - May 2024
I explored financial risk estimation for U.S. federal bonds using both classical and quantum algorithms. Analyzing monthly interest rate data from 1963 to 2024, I employed Monte Carlo simulation and Quantum Amplitude Estimation (QAE) to calculate Value at Risk (VaR) and Conditional Value at Risk (CVaR). While Monte Carlo provided a robust classical approach, QAE demonstrated the potential for greater computational efficiency. By comparing the performance of these methods, this work highlights the promising application of quantum computing in finance, paving the way for more efficient risk management techniques for U.S. government bonds.
Jul 2023 - Dec 2023
Developed an economic model to price cybersecurity insurance premiums by quantifying risk using CVSS vulnerability scores and behavioral risk factors. Analyzed real-world cyber threat data, mapped vulnerability severity to premium levels, and incorporated human-driven risk components to reflect practical security exposure. The model provides an adaptive pricing framework that aligns insurance premiums with evolving cyber threats and organizational risk behavior, improving accuracy and resilience in cyber-risk underwriting.
Jan 2023 - May 2023
Developed a system to generate personalized movie reviews using automated summarization techniques, incorporating user watch-history features. Initially experimented with transformer-based abstractive models (Longformer) but transitioned to a TF-IDF–driven extractive pipeline to improve output quality and genre relevance. Built custom datasets using IMDB and TMDB APIs, generated gold summaries via ChatGPT, and evaluated model performance using ROUGE metrics (avg score ~0.18, peak ~0.24). Demonstrated a structured ML workflow: data collection, feature engineering, model experimentation, evaluation, and refinement.
Jan 2023 – Apr 2024
Built a distributed stock-market analytics pipeline using Apache Hadoop, processing millions of historical price records to compute maximum stock values per ticker. Designed and implemented a custom MapReduce workflow to efficiently parse, aggregate, and analyze large-scale market data, achieving ~10× faster processing compared to a single-node baseline. Strengthened big-data engineering skills, including distributed file management (HDFS), batch processing, and performance-optimized data jobs for scalable financial analytics.
Developed ML models to forecast AUD-INR, JPY-INR, and CAD-INR exchange rates using regression techniques and Random Forests. Evaluated model performance using MAE benchmarks, with the Random Forest model achieving ~96% prediction accuracy, outperforming traditional regression approaches. Identified key limitations in linear regression due to skewed currency distributions, demonstrating the advantage of ensemble models in handling non-linear FX market behavior.
Built an option-pricing framework using real-time market data (1,000+ daily stock entries) and implemented Quantum Amplitude Estimation (QAE) in Qiskit alongside a classical Monte Carlo engine (10,000+ simulations) for payoff estimation. Demonstrated QAE’s computational advantage with ~90% faster execution (0.03s vs 0.28s), validating the potential of quantum algorithms for accelerating financial derivative pricing.
Here are some of my selected Projects I have done in the Past. Feel free to check them out.
I'm happy to connect, listen and help. Let's work together and build something awesome. Let's turn your idea to an even greater product. Email Me.