Skip to content

Deep learning recurrent neural networks to model bitcoin closing prices. Model One uses FNG indicators to predict the closing price, Model Two uses a window of closing prices to predict the nth closing price

Notifications You must be signed in to change notification settings

Maurolp15/Deep_Learning

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 

Repository files navigation

Deep Learning

My name is Oscar Lopez, I’m a student at the University of Miami FinTech Bootcamp Program.

In this activity, I was tasked with building and evaluating deep learning models using both the Fear and Greed Index (FNG) values and simple closing prices for a cryptocurrency coin (Bitcoin) to determine if the FNG indicator provides a better signal for Crypto than the normal closing data.

I used the skills learned in the class last week, I prepared the data for training and testing, built and trained custom LSTM RNNs, evaluated the performance of each model and visualized using hvplot.

In this assignment, I used the class exercises and google, specially stackoverflow to complete both start codes in the instructions and resolve the challenges I had, particularly with Google Colab as I was not too familiar with its imports and settings.

About

Deep learning recurrent neural networks to model bitcoin closing prices. Model One uses FNG indicators to predict the closing price, Model Two uses a window of closing prices to predict the nth closing price

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages