# Cryptocurrency Price Direction Predictor — Data

来源：https://www.kaggle.com/competitions/cryptocurrency-price-direction-predictor/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

Participants will be provided with a dataset containing historical OHLCV data for a specific cryptocurrency, recorded at a frequency of one minute, meaning there is one data point for each minute. The challenge is to predict the direction of the price movement for the next timestamp.

As historic cryptocurrency prices are not confidential, the public leaderboard targets are publicly available and are provided as part of the competition dataset. Expect to see many people submitting perfect submissions for fun. Accordingly, the active phase public leaderboard for this competition is not meaningful and is only provided as a convenience for anyone who wants to test their code. In order to do the final evaluation of the participants' solution, the code & model needs to be submitted and will go through separate evaluation. This serves as a check that no look ahead is involved. 

The dataset includes the following columns:
*  **timestamp**: A timestamp for the minute covered by the row.
*  **open**: The price in USDT at the beginning of the minute.
*  **high**: The highest price in USDT during the minute
*  **low**: The lowest price in USDT during the minute.
*  **close**: The price in USDT at the end of the minute.
*  **volume**: The number of crypto asset units traded during the minute.
*  **quote_asset_volume**: The total value of the traded shares in USDT during the minute.
*  **number_of_trades**: The number of trades that took place during the minute.
*  **taker_buy_base_volume**: The total amount of the crypto asset that was bought by takers during the minute.
*  **taker_buy_quote_volume**: The total value in USDT that was spent by takers to buy the crypto asset during the minute.
*  **target**: The direction of price movement from the current to the next minute. 1 stands for a positive price change and 0 for no or a negative price change.

## Files

*   **train.csv** - The training data set.
*   **test.csv** - The test data set, used for the leaderboard.
*   **sample_submission.csv** - An example of how the submission csv file should look like.