Inspiration
What it does
This web app recommends buying or selling a user-chosen stock based on sentiment analysis from news headlines using vaderSentiment, a machine-learning algorithms.
How we built it
For front end we used react js with bash to insert our python scripts from the back end. Using vaderSentiment and the google API, we searched for the first two pages for any keyword for a company and observed the sentiment for the articles that came about.
Challenges we ran into
Optimization. The MAJOR problem was optimization. With machine learning modles, when connecting to the front end, the optimization was...less than ideal. It resulted in a very long load time
Accomplishments that we're proud of
What we learned
What's next for Stock Rec
Increase variety of sources used for sentiment analysis.
Log in or sign up for Devpost to join the conversation.