Data

Tools

Indexes

Applications

Experiments

Open Source Science

aaai-ai-fin-23

Code Repository and general info for AAAI-AI-Fin'23 paper "Short-term prediction for Ethereum with Deep Neural Networks and statistical tests"

https://github.com/eduardojoselopesgit/aaai-ai-fin-23

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (9.6%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

Code Repository and general info for AAAI-AI-Fin'23 paper "Short-term prediction for Ethereum with Deep Neural Networks and statistical tests"

Basic Info
  • Host: GitHub
  • Owner: eduardojoselopesgit
  • Language: Jupyter Notebook
  • Default Branch: main
  • Homepage:
  • Size: 29.6 MB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created over 3 years ago · Last pushed over 3 years ago
Metadata Files
Readme Citation

README.md

"Short-term prediction for Ethereum with Deep Neural Networks"

Table of contents

General info

Code Repository and general info for AAAI-AI-Fin'23 paper. The main contribution of this research is to compare state-of-the-art deep learning architectures to predict Ethereum cryptocurrency close price against an ARIMA model with statistically validated results.

Technologies

Project is created with:

Software * System: Windows Version 10.0.19041 * Anaconda Navigator 2.1.1 * Jupyter notebook server version 6.4.6 * Python 3.7.11 (default, Jul 27 2021, 09:42:29) [MSC v.1916 64 bit (AMD64)] * IPython 7.31.1

Hardware * Processor: Intel64 Family 6 Model 165 Stepping 5, GenuineIntel * Physical cores: 10 - Total cores: 20 * Max Frequency: 3696Mhz - Current Frequency: 3696Mhz * Total memory (GB):32 * GPU Information: NVIDIA GeForce RTX 3090 - Total memory: 24576.0MB

Main packages * psutil version 5.8.0 * GPUtil version 1.4.0 * platform version 1.0.8 * numpy version 1.21.5 * pandas version 1.3.4 * torch version 1.10.2 * logging version 0.5.1.2 * darts (u8darts) version 0.17.1

Folders

  • /model: .ipynb files used for model calculation. Filename convention: AvBC-EPOCHSD-E-F-G-H.ipynb, where:
  • A anb B: code versioning.
  • C: cryptocurrency considered (ETH = ethereum).
  • D: number of epochs.
  • E: look-back sliding window.
  • F: forecast window size (hours).
  • G: batch size.
  • H: deep learning model.
  • /data: .csv file with Ethereum (ETH) timeseries information.
  • /results: spreadsheet file containing model results for different models and random seeds considered on model calculation. Table 4 on the referred paper reflects the median values for MSE, MAE, RMSE, and MAPE for each deep learning model.

Setup

To run this project, remember::

``` 1. Change the folder destination on the .ipynb files for the .csv file containing ETH timeseries information.

```

Contact

Created by eduardo.lopes@me.com - feel free to contact me!

Owner

  • Login: eduardojoselopesgit
  • Kind: user

Citation (CITATION.cff) 

# This CITATION.cff file was generated with cffinit.
# Visit https://bit.ly/cffinit to generate yours today!

cff-version: 1.2.0
title: >-
  Short-term prediction for Ethereum with Deep Neural
  Networks and statistical validation tests
message: >-
  If you find this research and software useful,
  please cite it using the metadata from this file.
type: software
authors:
  - given-names: Eduardo
    email: eduardo.lopes@fei.edu.br
    affiliation: Centro Universitário FEI - Brazil
    family-names: Lopes

GitHub Events

Total
Last Year