A data analytics case study on India’s Quick Commerce (Q-Commerce) market. This project explores customer behavior, delivery trends, product insights, and operational performance using a simulated dataset. Focused on deriving actionable business insights for strategy and growth in the Q-Commerce sector.

Vendor churn prediction and prevention system for Q-commerce. Predicts which restaurants will go inactive using operational KPI patterns, enabling commercial intervention that reduced vendor churn by roughly 62% in pilot deployment across 17K vendors.

Gym environments for logistics tasks that can be described as "Move something from A to B"

Zynvaro — AI-Powered Parametric Income Shield for India's Q-Commerce Gig Workers | Guidewire DEVTrails 2026 | Team AeroFyta

A frontend project about a Q-commerce and delivery company

Mimicing the operational flow of modern quick-commerce

Basket-level routing engine for Indian q-commerce: decides whether to buy a grocery basket from one provider or split across two to minimise true total cost (fees + min-order constraints), and explains why. Entity-resolution matching engine + constrained optimizer. FastAPI + Next.js. Mock data by design.

Noon — MENA e-commerce marketplace and digital lifestyle super-app (UAE / KSA / Egypt)

Competitive analysis of 8 Indian Q-Commerce platforms across 1M synthetic orders — EDA, statistical testing, and operational efficiency modelling in Python.