Inspiration
The fintech industry is growing rapidly, in relation with the ever-growing computing sections of Machine Learning and Artificial Intelligence. Traditional methods of stock analysis might seem a little overwhelming and inaccessible to many due to its natural complexity and learning curve. The ultimate goal is to bridge the gap between technology and finance, making investing more accessible. We want to bring out the symphony behind the madness of the raw data, and to help our users reach their tailored financial goals based on the generated predictive insights.
What it does
It is a multi-faceted web application that uses machine learning algorithms to predict the price (including sentiment values and neural networks) of certain stocks that can be added to a user's watchlist, a news API to deliver new perspectives, and real-time stock data.
How we built it
We built it using firebase for the database, flask for the backend, react and html for the front end, and we used a LSTM neural network and sentiment model for the machine learning models.
Challenges we ran into
The time constraint limited our ability to work on all of the features to the extent that we wanted to. For example, we wanted to add a social network aspect where users can have watch parties to look at stocks together.
Accomplishments that we're proud of
Our ML error values we're within acceptable ranges. We made something unique with our sentiment value model. Also, we integrated a news API to provide up to date information for our users.
What we learned
We learned about various learning models, different APIs, different ways to design a website, and most importantly how to collaborate as a team
What's next for IntelliStock
Creating the previously mentioned social aspect and fully optimizing it for user functionality.
Log in or sign up for Devpost to join the conversation.