Hello World ✌🏻
I am Ayush. I am a student, a teacher, and a practitioner of data science.
Here I blog/jot/dump/scatter ideas/muses/learnings/experiences on all things data and software.
I am based in Nepal 🇳🇵. When I am AFK, I am lifting weights. I am currently building husig.ai
Posts
What is the least number of features to remember to be safe?
Demo for Cheers AI, an AI enabled tool for prediction of Diabetic Retinopathy and Glaucoma based on fundus images. This tool is being used by BP Koirala Eye Foundation (Hospital for Children, Eye, ENT and Rehabilitation Services or CHEERS) to detect blindness caused by diabetic retinopathy (which is preventable if detected early).
The stages in the analytics process is filled with moments of success and failures. There are some instant gratifications during the process, where a begginer like myself might construe a non success as success, due to some kind of judgement error.
Analytics is extremely relevant in all aspects of ride-hailing. In this project, I merely covered a few use cases, with one or two relevant models. Even with this brief exploration, I can conclude that analytics can lead to better outcomes for both drivers and passengers.
georgia tech /
data viz /
analytics /
tootle
analytics in ride sharing /
tootle /
nepal /
analytics /
isye-6501 /
ride hailing /
ride sharing /
regression /
optimization /
eda
eHamroPasalmandu is a fictional eCommerse based in Nepal. If it were operating for a year, this is what the data would look like (kind of, sort of).
This is a starter code for Twitter sentiment analysis. Not to be used in prod.