Divorce is expensive in Canada! So many factors come into place and divorce is the last option a couple should opt for. To help you decide whether or not to make the harsh decision, we made a web app that predicts whether your relationship would provide fruitful.

What it does

RideOrDie(formally called Divorce Detector) is a web app developed on a machine learning algorithm that predicts whether your relationship seems to be going well, or not.

How we built it

We struggled a lot in the beginning, since this was our first Hackthon in university. For the first few hours, we were trying to figure out a starting point and find a model that seems to fit our needs. Then we used a dataset to train the model which proved to be accurate, and used HTML and CSS to build the front end of our application. Finally, we struggled on Flask and Python to work on the back end.

Challenges we ran into

We didn’t have any experience with AI before this Hackathon and ¾ of us weren’t even comfortable with Python. We struggled a lot at first since we didn’t know where to start. But with the help of the mentors and a lot of youtube video tutorials, we eventually figured it out, even though there are still a lot of flaws in our implementation.

Accomplishments that we're proud of

We are proud of our perseverance. At some point, we wanted to give up. But we didn’t! We are glad that we have learned so much through the project and we are happy with the results.

What we learned

We learned about the basics of AI and training machine learning models. We also discovered a lot of AI resources thanks to the workshop and the mentors. We also learned a lot about Python and its frameworks, HTML and CSS.

What's next for RideOrDie

We still have to work on perfecting the backend of the web app. It's only functional for now, but the images disappeared. Hopefully, we’ll have a complete web app at the end!

Share this project: