Sharpe Ratio
PublishedEfficiency: how much pace does a driver extract per unit of chaos?
Mathematics & Statistics · Purdue · Class of 2027
Prabhat M
Building toward quantitative research — rigorous models that explain why, not just predict that.
Work spanning quantitative finance, sports analytics, and applied machine learning.
- Focus
- Quant Research · Quant SWE
- Based
- West Lafayette, IN
- Status
- Open to FT 2027
10Published articles
3Internships & research roles
CitedIn peer-reviewed research
501(c)(3)Non-profit co-founded
01
About
Currently
SLMs and Agentic AI intern at Hexaware Technologies (Iselin, NJ). Finalizing the QuantF1 methodology paper for arXiv submission. Preparing FT applications for quant research and quant SWE roles.
I'm a Math and Statistics senior at Purdue, graduating May 2027. My work sits at the intersection of quantitative finance, sports analytics, and applied machine learning. I'm most interested in building rigorous models that explain why something happens, not just predict that it will.
Over the past two years I've self-built an implementation library covering the core syllabus of a graduate-level quantitative finance program — option pricing through exotics, credit risk models, factor models, portfolio optimization, time series analytics. More recently, I've been developing QuantF1: a quantitative performance attribution framework for Formula 1 that applies risk-adjusted finance metrics to driver evaluation. The methodology paper will be on arXiv in August 2026.
Co-founder of UltraRice, a registered 501(c)(3) non-profit working on rice fortification for malnutrition in India, funded by Tyler Cowen's Emergent Ventures India program. Selected participant in the 2026 IMC Trading US Chess Academy.
02
Toolkit
The languages, models, and infrastructure behind the work below — grounded in shipped projects, not coursework checklists.
Languages
- Python
- C++
- SQL
- R
- Java
Quant & Finance
- Black-Scholes
- Monte Carlo (Exotics)
- Factor Models
- Markowitz / Black-Litterman
- Credit Risk (Merton)
- ARIMA / GARCH
- Alpha / Signal Research
- Backtesting
- Kelly Sizing
Machine Learning
- TensorFlow
- XGBoost
- AutoGluon
- Pandas · NumPy · SciPy
AI & NLP
- FinBERT / VADER
- Neurosymbolic AI
- Adversarial Robustness
- RAG / Vector DBs
Statistics & Methods
- Hierarchical Bayesian
- Monte Carlo
- Hypothesis Testing
- Regression
- Time Series
- Walk-Forward Validation
- Newey-West HAC
- Multi-Agent Simulation
Systems & Infra
- Docker
- AWS
- GCP
- CI/CD · GitHub Actions
- SQLite
- React
- Git
03
Featured Research — QuantF1
FlagshipA hierarchical Bayesian framework for understanding Formula 1 driver performance under uncertainty — separating driver skill from machinery using 2022–2025 telemetry. QuantF1 applies risk-adjusted finance metrics to driver evaluation and performance attribution.
The Series
- The Sharpe Ratio of a Driver — What Quant Finance Can Teach Us About Formula 1 Performance
- The Sortino Ratio of a Driver — Measuring Controlled Aggression in F1
- The Execution Profile of a Driver — Measuring Performance Beyond the Results Table
- The Alpha of a Driver — Separating Skill from Machinery in Formula 1
- The Physics of Failure — Measuring Drawdown and Recovery in Formula 1
Analytical Framework
Sortino Ratio
PublishedControlled Aggression: which mistakes actually matter?
Execution Profile
PublishedBehavior: how is performance delivered?
Alpha
PublishedSkill vs Machinery: separating the driver from the car.
Drawdown and Recovery
PublishedResilience: what happens when things go wrong?
Regime Sensitivity
Forthcoming · arXiv Aug 2026Context: when does a driver's execution work?
Consistency
Forthcoming · arXiv Aug 2026Repeatability: is this structural skill or situational brilliance?
04
Quantitative Finance
Implementation work spanning derivatives, portfolio construction, and systematic trading — including a production prediction-market forecasting system currently paper-trading via daily GitHub Actions.
Quant-Finance Repository
Quant-Finance
End-to-end research and implementation library covering Black-Scholes, Monte Carlo for Asian/Barrier/Lookback/Rainbow exotics, Merton credit model, factor models, portfolio optimization, and time series analytics.
- Options pricing — Black-Scholes & Monte Carlo for Asian / Barrier / Lookback / Rainbow exotics
- Credit risk — Merton, Black-Cox, Jarrow-Turnbull
- Factor models — CAPM, Fama-French 3/5, Carhart, AQR style premia
- Portfolio optimization — Markowitz, Black-Litterman, reinforcement learning
- Sentiment-driven trading pipeline (VADER + FinBERT); backtesting engine with realistic transaction costs; live paper-trading bot
- Companion multi-asset signal track — walk-forward, out-of-sample validation; ~0.7 Sharpe on the Numerai signal competition
- Financial Models
- Portfolio Management
- Trading Strategy
- Time Series
- Live Paper Trading
ML@Purdue · Applied Prediction Markets
TSA Forecasting for Kalshi
Contributor on ML@Purdue team project (PM: Eubene In) building a production forecasting system for Kalshi's weekly TSA checkpoint contracts. Owned the ARIMA/SARIMAX baseline track and walk-forward benchmark harness; implemented quarter-Kelly position sizing.
- Best baseline (ENSEMBLE_BASIC, fold-wise retraining): R² 0.67 · MAE 142.7k · 95.88% PI coverage
- Empirical finding: retraining frequency matters more than model complexity for this problem
- Production track — AutoGluon ensembles (~105M params) with Newey-West HAC standard errors
- Paper-trading since March 2026 via GitHub Actions
Systems · In Progress · Ships Aug 2026
C++ Matching Engine
Minimal price-time-priority matching engine in C++ with order book, trade logging, and performance benchmarks. Demonstrates low-latency systems engineering relevant to quant SWE roles.
Public repo link on ship.
05
Experience
SLMs & Agentic AI Intern — Hexaware Technologies
Building applied ML in the life sciences practice, focused on small language models (SLMs) and agentic AI systems for production workflows.
Research Assistant — Purdue College of Liberal Arts Research Academy
Designed large-scale multi-agent simulation experiments for statistical analysis and hypothesis testing under partial information, with reproducible Python pipelines for out-of-sample evaluation. Modeled sequential decision-making under uncertainty — achieving a 25% improvement in task accuracy through data-driven intervention design.
Software Engineering Intern — Hotkeys Holding LLC
Engineered low-latency retrieval pipelines in Python using vector databases and Gemini APIs — cutting document-lookup latency ~90% and enabling sub-200ms real-time inference. Designed caching and batching workflows that reduced LLM response time 95% on cache hits, with end-to-end instrumentation for latency, throughput, and retrieval quality.
06
Education
Purdue University
B.S. Mathematics & Statistics
Quantitative Coursework
- Mathematical Probability
- Statistical Theory
- Introduction to Time Series
- Linear Algebra
- Discrete Mathematics
- Data Structures
- Computer Architecture
- Assembly Language
Planned · Fall 2026 Foundations of Analysis · Elementary Stochastic Processes
Competitions & Honors
- Putnam (2025)
- ICPC Regional (2024)
- IMC Trading US Chess Academy — 7th, Qualifier Bracket (2026)
- CICSE Chess Nationals — Tamil Nadu Rep (2022)
07
Machine Learning & Neurosymbolic AI
Applied ML systems, neurosymbolic reasoning, and focused research artifacts.
Neurosymbolic AI
Disease Classification and Triage
Production-grade Flask application for symptom-to-diagnosis inference, integrating symbolic clinical reasoning with neural pattern recognition. Containerized via Docker with CI/CD workflows for reproducible deployment.
Explore RepositoryAdversarial ML
Neural Network Robustness
Focused study of adversarial attacks (FGSM, PGD, C&W) and defense mechanisms for deep learning models.
Explore RepositoryRecommender Systems
Movie Recommendations with Deep Learning
Hybrid neural network combining collaborative and content-based filtering using TensorFlow Recommenders, addressing cold-start and sparsity.
Cited in Lavreniuk and Potapova (2025), Applied Information Technologies, Vasyl' Stus Donetsk National University.
Explore RepositoryEssay
Beyond Deep Learning: The Rise of Neurosymbolic AI
Introduction to hybrid symbolic-neural systems, written March 2023. Predates the recent neurosymbolic AI wave by about 18 months.
Read Essay
08
Writing
Ten articles across three tracks: QuantF1 research, applied machine learning, and neurosymbolic AI.
QuantF1 Research
Risk-adjusted driver evaluation — the full series is listed in section 03.
- The Sharpe Ratio of a DriverOct 2025
- The Sortino Ratio of a DriverOct 2025
- The Alpha of a Driver2024
Machine Learning
Neural networks, recommenders, and adversarial robustness.
Neurosymbolic AI
Hybrid symbolic-neural systems, written before the wave.
09
Background
UltraRice — 501(c)(3) Non-Profit
Co-founded at 17 to develop ultrasonic rice fortification technology targeting India's 250M+ malnourished. Secured $20,000+ in non-dilutive grant funding from Emergent Ventures India (Tyler Cowen, Mercatus Center, George Mason University) on the basis of independent research. Built a Python (Pandas, SciPy) analytics pipeline to validate hypotheses through controlled trials. Public financials at bank.hackclub.com/ultrarice.
The Knowledge Society (TKS)
Globally selective youth innovation program (alumni at Microsoft, Neuralink, IBM). UltraRice originated here as an end-of-year moonshot project.
Chess
Selected for the IMC Trading US Chess Academy 2026 — one of 20 brackets nationwide; finalists meet World Chess Champion Magnus Carlsen. 7th-place finish in the qualifier bracket. Previously Tamil Nadu state representative at the CICSE Chess Nationals (2022).
10
Let's Connect
I'm always interested in discussing research, collaborating on projects, or exploring new opportunities in quantitative finance, machine learning, and AI.