Predict ETH challenges
Project description
Predict ETH
This is a challenge to predict the price of ETH. With prize $$. It uses ocean.py library.
Predicting ETH accurately helps to make $ in buying / selling ETH, DeFi trading, yield farming or DeFi protocol development. And, you can sell your predictions as a datafeed, for others to do the same.
Then the challenge is: how accurately can you predict ETH?
Current / future challenges
- Challenge 3 - predictions due Feb 20, 2023
Example End-to-End Flows
These are example full submissions to the challenge. You can use any of them as a starting point.
- Simple: To-the-point example, with simple input data (just ETH price) and simple model (linear dynamical model)
- Model optimization: Same as Simple with added optimization using cross-validation to select best hyperparameters.
- Compare models: Build models that predict 1-12 hours ahead in one shot. Compare linear, SVM, RF, and NN models.
Example Data Sources
These are examples of how to get data from various places. Each place has its own benefits.
Get ETH price data:
- Via Binance direct - most direct, but specific to Binance
- Via ccxt + Binance - unified API across 40 exchanges
- Via Ocean + Binance - unified API across 500+ data & compute services
- Via Ocean + TheGraph - like previous, but uses a GraphQL-shaped query
Inspiration: ideas for data & modeling
Here are ideas to get even more accurate results.
- More data sources
- Modeling approaches
- Articles on predicting ETH, etc
Inspiration from algorithmic trading
Getting into the head of a trader might inspire you in predicting ETH.
To help with that, the algorithmic trading flow README does a walk-through of the "Freqtrade" open-source trading tool with a custom trading strategy.
Appendix: Past challenges
- Challenge 1 - predictions due Oct 16, 2022
- Challenge: web3 ATL hackathon - predictions due Nov 6, 2022
- Challenge 2 - predictions due Dec 11, 2022
Appendix: Predict-eth library
Predict-eth is a library on pypi.
To install: pip3 install predict-eth
To further develop it:
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file predict_eth-0.1.1.tar.gz
.
File metadata
- Download URL: predict_eth-0.1.1.tar.gz
- Upload date:
- Size: 24.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.1 CPython/3.10.6
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 9c8253213610c00650a6b54c0579f834ad193e244a7eeb23639a0a7de757e7ad |
|
MD5 | 8a46d9416ec514d8a343433ffe0b4f29 |
|
BLAKE2b-256 | 9f9e837bdefd0d21b7ff23c01d1fd6995669c794cda397411ff82f833c3741ca |
File details
Details for the file predict_eth-0.1.1-py3-none-any.whl
.
File metadata
- Download URL: predict_eth-0.1.1-py3-none-any.whl
- Upload date:
- Size: 5.6 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.1 CPython/3.10.6
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | f4f1a3f4dc3fa9d0a0a0b6ed05f2f0d65d9fa6a124fe864b66c40705e3872201 |
|
MD5 | 28563307de4f3beecda1b7f5409b059c |
|
BLAKE2b-256 | d0f0b8fc7ffc2b14753ccfd7d12160295ba1e3c3ab8f837f23f6bb97357d1712 |