Prediction model on BTC prices with deployment

Hi guys. I will love to receive feedback from this project, any type of feedback are welcome

This is the GitHub repository

I did a prediction model using XGBoost to predict if the BTC price will hit a target of that day, the prediction was made as a classification problem. The model was basic as I only use 5 features as predictors.

The most interesting part of the project was the deployment. I was able to upload the model to AWS and generate a prediction service to run the model on daily basis and have the prediction at 9am EST time.

Next steps:

  • Use the stock price prediction webinar to improve the accuracy of the model
  • Use the Azure course to deploy the model using Azure instead of AWS
3 Likes

Great Project @PastorSotoBlanco, I have really learned a lot from it, especially how you were able to structure your readme.md in your GitHub. my only suggestion is to work on your visualization as some of them are really small.

Great project overall :muscle:

Hi @OlutokiJohn Thank you so much for your feedback. Do you mean the charts on the demonstration part in the README file?

No on the main notebook itself.

Ok. Great! Thanks for your feedback!

1 Like