We wanted to create a tool for companies to empirically evaluate the level of systemic discrimination in their company without having to hire a data analyst. The program can also clue in on which managers are causing systemic discrimination giving employers an avenue on what is causing the problem.
What it does
It takes in company data as a CSV file and checks for systemic discrimination in pay, and promotion decision's and compares the data to national industry average's.
How we built it
We built it using Python and the Python libraries: Pandas and Scipy
Challenges we ran into
Not everyone on the team had experience working with Pandas so some of us had to learn it. Additionally the time constrains of a hackathon made it harder to finish in time and implement all the functionality we wanted. We had to make the decision to cut some parts of the program to beat time constraints. There also isn't any public data for what we needed so we needed to rely on synthetic data.
Accomplishments that we're proud of
This was our first hackathon! and were proud that were making it to presenting. Were also proud that me managed to pick something that fit the theme, is in our opinion a cool project and that we had the tech skills to implement.
What we learned
For most of us it was our first time working on a coding project as a team and we learned how to use Github better.
What's next for Systematic Discrimination Checker
-Encrypt employee ID's to improve privacy -Gather more national industry benchmarks -Add a UI to make it easier to use -Add support for missing values
Log in or sign up for Devpost to join the conversation.