Predictor Bot

Training the prediction model
Predictions for Apple stock price
Predictions for Netflix stock price
Weather forecasts
Predicted price for Apple stock

Inspiration

We wanted to make a bot that can predict things for us, and to learn the basics of machine learning and API use.

What it does

We built a chatbot for terminal and discord that can predict stock prices as well as tell you suitable times to go outside for. The terminal version is a chatbot that will talk and converse with the user using NLP, while the discord version responds to commands like any other discord bot. We used web requests to get the weather data and trained a recurrent neural network to predict the stock price.

How we built it

We built it by having each feature be a separate module, and then merging these features into one main file that contains the chatbot, weather predictor, and stock price predictor.

Challenges we ran into

We ran into two challenges, the first one was getting the stock market predictions to be accurate, and the second one was formatting the text of the weather bot correctly.

Accomplishments that we're proud of

We have created a bot that can make accurate and useful predictions as well as interact with the user all with machine learning.

What we learned

We learned how to train machine learning models for making predictions and NLP. We gained experience in properly using try-except blocks of code and formatting data and text.