The following are the projects that I worked on or have been working on. Most of them are technical implementation projects and I enjoy them very much!
# VIAplanner (Open Source)
VIAplanner is a tool designed by students at the University of Toronto to help the community. We desire to enhance the course selection process.
# utmhacklab.tech (Open Source)
I had the honour to contribute to the building process of utmhacklab.tech by building the MAT102 page for first year students. Most first year has little experience with mathematical proof, and I provided resources that could help them in an entertaining way.
# Isomo Recruitment
A startup aiming to eliminate the unintentional biases (e.g. race, gender) in the hiring process. On this platform, only your skillsets matter.
The current recruitment process could be time consuming and sometimes contain unintentional bias. People can fall prey to collective decision making errors similar to “herd behavior’, social hierarchy bias, and social conformity bias. These above challenges have become obstacles for companies that are striving to create a diversified environment through fair recruitment.
We thrive to achieve true equality during the recruitment process by filtering out potential information that could lead to biases(e.g. Race, gender) from the applicant. This allows recruiters to simply analyze applications based on skillsets, experience, and performance.
# Resonance Investment
Resonance analyses personal and investment traits to make the best matches between an individual and an advisor. We use basic information any financial institution has about their clients and financial assets as well as past interactions to create a deep and objective measure of interaction quality and maximize it through optimal matches.
The whole program is built in python using several libraries for gathering financial data, processing and building scalable models using aws. The main differential of our model is its full utilization of past data during training to make analyses more wholistic and accurate. Instead of going with a classification solution or neural network, we combine several models to analyze specific user features and classify broad features before the main model, where we build a regression model for each category.