harivansh-afk/CryptoCurrencyPredictionLSTM
1
0
Fork 0
mirror of https://github.com/harivansh-afk/CryptoCurrencyPredictionLSTM.git synced 2026-04-15 07:04:46 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Update README.md

Browse source
This commit is contained in:
harivansh-afk 2024-11-01 16:21:31 -04:00 • committed by GitHub
parent 5e1aaa8833
commit 7520dee148
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 6 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

6
README.md
View file

@ -12,6 +12,12 @@ The crypto market is renowned for its turbulence, dynamic, and nonlinear nature,
LSTM, a type of recurrent neural network, is particularly promising for analyzing sequential data like time series. This research builds on previous studies, which primarily focus on a few cryptocurrencies and outdated datasets, by incorporating more recent data and a broader range of currencies.
## Instructions
- To Run this file, you must first download the dataset that this is based upon
- The dataset can be found on [Kaggle](https://www.kaggle.com/datasets/jessevent/all-crypto-currencies) and download as a zip file
- Once the file has been downloaded you must add it to the same folder as the .ipynb file on your computer
- The project can then be run and tested on this dataset
## Results
Our results demonstrate an accuracy rate of 50-60%, highlighting the volatility of the cryptocurrency market. The LSTM model showed a slight improvement over other models, indicating its suitability for time-series data. We implemented our models using Python libraries such as Sklearn, Keras, and Tensorflow, executing them on the JupyterLab platform. The best model was selected based on RMSE and MAPE values.