Inspiration
During our internship periods, we lived in metro cities for a couple of months and we rented out flats with our friends for which we had to pay a huge amount for the first month of our stay this was due to a high brokerage cost thus this let us find a solution so that people like us doesn't,t have to face such problem in future.
What it does
It predicts the optimized rent for a flat that is no loss of your hard earned worth
How we built it
"Using ML algorithms" we used number of algorithms like
- Linear Regression 2.Decision tree
- Random Forest 4.Gradient boost regression
After implementing all we concluded that gradient boost regression is providing the most accurate result for the problem next we integrated it with flask to create a user interface
Challenges we ran into
- It took a lot of tuning and selection of approaches to optimize the accuracy.
- selecting the appropriate attributes for best accuracy was a time-consuming task.
- integrating ML model with flask was absolutely a challenging task
Accomplishments that we're proud of
After all, training, testing and integrating, We achieved an accuracy rate of 88.5%
What we learned
To work as a team and to utilize each of our skills to complement each other's work, learn new approaches to resolve the problem statement, delivering a good product on time
What's next for No Broker
It can help seekers to find the best places to live at the best price.
