Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/etienne-bobo/predict-bitcoin-price
predict price of bitcoin using time series
https://github.com/etienne-bobo/predict-bitcoin-price
conv1d keras nbeats tensorflow timeseries-forecasting
Last synced: 28 days ago
JSON representation
predict price of bitcoin using time series
- Host: GitHub
- URL: https://github.com/etienne-bobo/predict-bitcoin-price
- Owner: Etienne-bobo
- Created: 2023-11-20T20:27:15.000Z (12 months ago)
- Default Branch: main
- Last Pushed: 2023-11-20T21:11:01.000Z (12 months ago)
- Last Synced: 2024-04-23T00:17:49.275Z (7 months ago)
- Topics: conv1d, keras, nbeats, tensorflow, timeseries-forecasting
- Language: Jupyter Notebook
- Homepage:
- Size: 554 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Predict-bitcoin-price
Data from = https://www.investing.com/crypto/bitcoin/historical-data
Bitcoin prices from 2010-07-18 - 10/24/2023
Data: Daily Historical price of Bitcoin over the past years
Results of modeling experiments
- Model 1 = Univariate Deep learing Dense model with horizon=1 and window_size=7
- Model 2 = Univariate Deep learing CONV1D model with horizon=1 and window_size=7
- Model 3 = Multivariate Deep learing Dense model with horizon=1 and window_size=7
- Model 4 = Univariate Deep learing Dense model(NBeats algo) with horizon=1 and window_size=7
Replicating the [N-BEATS: NEURAL BASIS EXPANSION ANALYSIS FOR INTERPRETABLE TIME SERIES FORECASTING](https://arxiv.org/pdf/1905.10437.pdf) paper- Model 5 = Univariate Deep learing Dense emsemble model with horizon=1 and window_size=7
Fit on 3 differents metrics with different random initialization
![Alt text](image.png)