This project explores the relationships between a perfume's fragrance notes and the subjective experience of their emergent accords using a variety of statistical methods including mutual information, principal component analysis, and multilabel classification.

Aromatica: Recommendation Service

The original proposal as accepted by the Urbit Foundation

A fragrance classification model based on a multiclass classification framework from scikit-learn, where I use my own handcrafted fragrance family and fragrance note dataset to predict which of the four fragrance families (Fougères, Orientals, Chypres, and Gourmands) a scent belongs to, based on its notes.

Static business website for a fragrance brand. Built with HTML and CSS to showcase products, services, and contact details.

This project contains code, data, and models for predicting the gender category (Male, Female, Unisex) of fragrances using machine learning techniques, based on rich metadata scraped from fragrantica.com

Repository for Scent Atlas, an interactive fragrance catalog and exploration platform.

This project is a Flutter application designed to manage a waitlist for a perfume product. It was an 8-hour non-commercial hackathon project. It includes features such as localization and integration with Firebase for saving waitlist data.