Inspiration
What it does
We predict the revenues of high growth software stocks...
How I built it
We tried a variety of models, including Lasso regression, neural nets, and gradient boosters. Gradient boosters performed the best.
Our final model predicts revenue one year in the future to about a factor of 1.44.
Challenges I ran into
Cleaning and preparing data took more time than expected.
Accomplishments that I'm proud of
What I learned
What's next for Predicting forward revenues of high growth software stocks
Built With
- keras
- numpy
- pandas
- python
- scikit-learn
- xgboost
Log in or sign up for Devpost to join the conversation.