# Analysts@Emory — Data

来源：https://www.kaggle.com/competitions/emory/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

Coding language: Python
Note: You don't have to use Python for visualization

Datasets: cryptocurrency (BTC, ETH, USDT, DOGE, SHIBA INU) price and volume information from coinmarketcap.com, the prices of other cryptocurrencies can give you insight on market changes.
Goal: predict the price of BTC in the next hour where 0=price drops by 0.02% or 1=price goes up by 0.02%

REMEMBER that no one can predict bitcoin change at 100% accuracy. The goal is to make the accuracy as high as possible.

Participants should be able to answer these types of questions after reading the data description:
- What am I predicting?  
- What variables are available for prediction?
- What level of granularity is there in the data?

The dataset has tracked and produced files for hourly time series pricing data for the crypto market. Each file is in CSV format and can be imported automatically by Python scripts or other automated processes. 

In each file, you will find the following columns. This OHLC (Open/High/Low/Close) pricing data is taken from the daily exchanges.

Unix Timestamp - Also known as "Epoch Time". You can convert it to your local time.
Date - This timestamp is in UTC(Universal Time Coordinated) Time Zone
Symbol - The symbol for which the time series data refers
Open - The opening price of the time period
High - The highest price of the time period
Low The lowest price of the time period
Close - The closing price of the time period
Volume (Crypto) - The volume in the transacted Ccy. Ie. For BTC/USDT, this is in BTC amount
Volume Base Ccy - The volume in the base/converted ccy. Ie. For BTC/USDT, this is in USDT amount
Trade Count - The unique number of trades for the given time period