# Crypto Market Anomaly Detection — Data

来源：https://www.kaggle.com/competitions/anomaly-class-detection/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

## Imbalance of the dataset

The given dataset for this competition is characterized by a significant class imbalance. This means that the distribution of the target variable, which represents the movement of stock prices, is highly skewed towards one or a few classes, while other classes have relatively fewer instances. It is important to be aware of this imbalance when developing your models and evaluating their performance. Consider applying appropriate techniques such as class weighting, oversampling, or undersampling to address this challenge and ensure that your models are capable of effectively capturing patterns across all classes.

## Columns

*   `result` - defines this way:
 - 0 - short/long/anomaly;
 - 1 - hold;

#### Categorical Columns

*   `RSI_signal`
*   `Stoch_O_signal`
*   `ichimoku_c_signal`
*   `fibonacci_signal`
*   `Bollinger_signal`
*   `exchange`

#### Numeric Columns

Basically they are all other columns in dataset. But I need to say a few special words about columns below:

*   `ichimoku_c_conversion_line`
*   `ichimoku_c_base_line`
*   `ichimoku_c_leading_span_a`
*   `ichimoku_c_leading_span_b`
*   `pivot_support_1`
*   `pivot_resistance_1`
*   `pivot_support_2`
*   `pivot_resistance_2`
*   `pivot_support_3`
*   `pivot_resistance_3`

The mentioned indicators represent various points of interest in price movement analysis. These indicators help traders and analysts identify potential areas of price reversals, support, and resistance, enabling them to make more informed decisions in their trading strategies.