Inspiration

Have you ever wondered how stock markets work? In the world of financial booms, busts and the chaos make predicting the market impossible. In the spirit of taking on the challenge for National Bank we aimed to create a stock prediction tool. We wanted to learn more about financial markets while implementing ML and learning some data science along the way!

What it does

BullsAI is a web application that predicts the behaviour of stocks during events of volatility. The web application can serve as a normal trading terminal providing technical indicators and information, while also providing the projection of the AI.

How we built it

It is built using Dash, Tensorflow, Google Colab and with extra sauce from HTML and CSS.

Challenges we ran into

We needed to understand the datasets, and the context of the challenge. It was the team's first finance related challenge and we needed to spend time to understand the terms.

Accomplishments that we're proud of

We were able to make use of a Long Short-Term Memory (LSTM) AI model to predict the behaviour of different stocks during time of crisis. We were also able to obtain the correlations and cross-correlations of the dataset to understand the impact of stock movements of different companies.

Built With

Share this project:

Updates