I build production data products and rigorous statistical analyses. My work spans API-driven web applications, forecasting, classification, databases, and applied machine learning.
I'm an MSc Data Science student at the University of Nottingham, where I expect to graduate in September 2026. I hold a First-Class Honours degree in Mathematics from the University of Delhi, and I work at the point where statistical theory meets practical data problems.
My recent work includes a live World Cup sleep-planning product built with Hermai.ai, a road-collision severity study selected as a teaching exemplar, seasonal ARIMA forecasts for East Midlands house prices, the privacy-first file converter DeltaConvert, and the LSTM currency forecasting application Stochastix.
I care about understanding how a model reaches its answer, testing it properly, and presenting the result clearly to technical and non-technical audiences.
Built an end-to-end data product during a University of Nottingham micro-placement. Pulled and validated 104 World Cup fixtures through Hermai.ai's API, modelled sleep disruption across time zones, and published the result as a live site. The production pipeline redeploys every six hours and stops the build when a data load is incomplete or invalid.
Privacy-first file conversion tool for images, documents, and OCR, all processed server-side. Built with Flask, deployed on Hetzner with Docker Compose, Nginx, and SSL via Certbot.
LSTM-based 30-day currency exchange rate forecaster. 29 trained models, React frontend with interactive Plotly charts, daily ECB audit cron job.
Chemicals: Per-type linear regression beating Random Forest (score 98, 1st of all groups). Trains: XGBoost on Sheffield–Nottingham increment (MSE 28,078). MATH4069 coursework.
Compared Logistic Regression, Random Forest, RBF SVM, and Multi-Layer Perceptron models on 29,628 UK STATS19 records. Built leakage-free per-fold pipelines under nested cross-validation, used Wilcoxon signed-rank tests for model comparison, and found Random Forest strongest on macro-F1. The module convenor selected the submission as a teaching exemplar for the next cohort.
Built two seasonal ARIMA models on ten years of monthly UK house-price data. Selected orders from ACF and PACF diagnostics, produced six-month forecasts with 80% and 95% prediction intervals, checked residuals with Ljung–Box tests, and wrote a one-page planning summary for a non-technical local-government audience.
PHP/MySQL hospital management system with role-based access, patient search, admissions, prescriptions, parking permits, and a custom audit trail. Graded Distinction at UoN.
Web scraping 2,000+ reviews with BeautifulSoup, NLP sentiment analysis, and Random Forest booking prediction model.
AI-powered financial chatbot parsing 10-K and 10-Q reports with rule-based logic to provide user-friendly corporate insights.
10-year exploratory analysis of 6 major banks' stock data (2014–2024) using Pandas, Matplotlib, and Seaborn.
Machine Learning, Statistical ML, Big Data, Databases, Time Series & Forecasting, and Data Science
Dissertation: A Complete Methodological Investigation of Mondrian Forest in Machine Learning.
SOUTH ASIA POSTGRADUATE EXCELLENCE AWARDFirst-Class Honours. Modules included Probability, Statistics, Economics, Mathematical Finance, Calculus, Linear Algebra, Mathematical Modelling, Differential Equations, Discrete Mathematics, C++, R, Mathematica, LaTeX, and HTML.
INSPIRE SCHOLARSHIP FOR TOP 1% NATIONALLYOne of two student data analysts engaged through the University of Nottingham micro-placement programme. Worked directly with the co-founder, built a production product from 104 API-supplied World Cup fixtures, added data-quality checks, and set up six-hourly redeployment through GitHub Actions.
Live project ↗QA on AI-generated mathematical models. Evaluated calculus and algebra outputs for hallucination and factual accuracy. Developed complex maths questions to improve model comprehension.
Built supervised and unsupervised ML models (linear regression, K-means clustering). Created detailed visualisations. Conducted 15 peer reviews and supported fellow interns.
Tutoring primary and secondary school students in mathematics. 100% pass rate in final exams. Focus on building problem-solving intuition through interactive, positive learning environments.
Active member of the University of Nottingham Hiking and Rambling Society. Regular group walks and weekend rambles provide balance alongside postgraduate study and support teamwork with students from a wide range of backgrounds.
Student member of the IMA, with an ongoing interest in applied mathematics, statistics, and the connection between mathematical reasoning and practical data work.