Built an ML framework that designers can use to figure out which aesthetic principles their specific users care about. Instead of applying generic design rules, test what actually matters to your audience. Made it open-source so designers can validate decisions with data instead of assumptions.
Predicted income from US Census data by systematically testing what actually improved performance versus what just looked sophisticated. Ensembled 5 cross-validation models instead of using one, optimized decision thresholds for class imbalance, and stripped out features that added noise. The process of figuring out what not to do taught me more than the final accuracy.














Building products at the intersection of Engineering, Design Strategy and Business Analytics
Built predictive simulation framework reducing engine testing time from 14 days to hours with 95% accuracy.
Led GTM strategy for autonomous underwater vehicle. Won 4 startup competitions securing funding.
ML framework quantifying aesthetic preferences. Study with 101 participants revealing data-driven design principles.
Neural network achieving 85.6% accuracy on Census data using ensemble of 5 k-fold models with optimized thresholds.
Random Forest models predicting career trajectories from 3,300+ alumni records to inform curriculum development.
Recommendation system using LLM to extract intent from natural language queries. Scores properties across environment, budget, capacity, amenities, and location with dynamic weighting. Built CLI and Streamlit UI handling 100+ properties with CSV export.
Migrated 1,270+ alumni records to modern CRM. Automated grant workflows achieving 57% growth in participation.
Founded campus health initiative. Organized 4 blood donation camps serving 300+ participants with 161 donors.
"Two roads diverged in a wood, and I took both,
then built a bridge between them."
Hover over markers to explore, click to step inside the story.
Where I learned to build things
Started with mechanical engineering, thinking I'd design machines. Learned CAD, simulations, product development. But I cared more about solving the right problems than building perfect solutions.
Built GT-Suite model for 4-cylinder diesel engine. Achieved brake torque error within ±3%, model accuracy >97%. Learned that technical precision matters, but understanding the system matters more.
Report →Stakeholder research revealed miners needed hands-free safety communication. Pivoted from inner-braces to glove-based haptic feedback after field study. First lesson in product-market fit.
Report →Designed impact-absorbing phone case using auxetic structures. Learned CAD, prototyping, and that good design requires understanding material properties as well.
Report →Cleaned 3,300+ messy alumni records. Built Random Forest models for career prediction. This project opened the analytics path.
GitHub →Where I learned to ask "why"
Added product design minor after realizing I cared more about people than machines. Learned ethnography, systems design, strategic frameworks. Discovered that good products start with understanding problems, not solutions.
Built ML framework to quantify aesthetic principles using YOLOv8. Study with 101 participants revealed simplicity and contrast drive preference. Proved you CAN quantify aesthetics, contrary to what everyone said.
View Details → GitHub →Led market research for autonomous underwater vehicle. Researched 22 competitors, interviewed potential users, won 4 government competitions. Learned ownership the hard way in messy startup environment.
View Details →Applied Nielsen's 10 heuristics across 5 core screens. Identified 47 usability issues with actionable recommendations. Learned to critique design systematically, not just say "it feels off."
Report →Analyzed India's semiconductor opportunity. Competitive analysis of 22 global players, market sizing, multi-phase roadmap. Learned to think about markets, not just products.
Report →Observed print shop operations to find bottlenecks operators couldn't articulate. Proposed automation based on actual workflow, not assumptions. First real ethnographic research project.
Report →Where I'm learning how to use models to solve probems
Currently at Rotman's Management Analytics program. Learning deep learning, recommendation systems, statistical modeling. Figuring out how to use data not just to measure what happened, but to understand what should happen next.
Built 2-layer neural network on Census data. Achieved 85.6% accuracy using ensemble of 5 k-fold models with optimized thresholds for class imbalance. First serious deep learning project.
View Details → GitHub →Built collaborative filtering system for vacation property matching. Learned recommendation algorithms, user preference analysis, and how to handle sparse data.
View Details → GitHub →Regression, hypothesis testing, A/B testing, experimental design. Learning when data actually supports a decision and when it doesn't. Most important lesson: knowing what you can't conclude.
Where everything comes together
Currently working on projects that combine product thinking, design, and analytics. Exploring ML and design thinking applications in Tech and Fincance, and figuring out what comes next. The journey continues - still learning, still building, still asking questions.
Built to tell my story authentically.
Looking for opportunities that value curiosity, systems thinking, and the ability to bridge technical and human problems. Probably in finance or tech.
Three years into mechanical engineering, I realized I was more interested in why people wanted things than how things worked. Working on the haptic glove project, I spent more time interviewing miners than designing the device. That's when it clicked - I cared about the people, not the machines.
Kept wondering if there was more beyond building things. This was where I moved to a more interdisciplinary approach. Learnt not just machines but also simulations, data science and modelling.
I have learnt everything theoritically, I wasn't sure which domain I should apply my skills to. Narrowed down to Finance and Tech based on a lot of thinking and networking!
I build products by asking questions first. Every project starts with understanding the problem space before touching code. It takes longer upfront, but I'd rather spend time thinking through edge cases than fixing broken assumptions later.
Outside of work, I move between creative outlets that keep me grounded. What matters most is finding ways to think differently, whether that's through movement, words, or just sitting with an idea until it makes sense.
Rotman School of Management · Master of Management Analytics
Learning to turn data into decisions
Graduate Ambassador, Business Design Club
B.Tech in Mechanical Engineering · Minor in Product Design
Where I learned to build things and question why they should exist
Alumni Affairs Secretary, MaRS Society, Footlights, NCC