ML Data Export

Export comprehensive feature-engineered data for machine learning training

Export Configuration
Configure your ML dataset export settings

Maximum 10,000 samples per export

Feature Information
115 total features per sample

Price Features (6)

closeopenhighlowvolumepriceChange

Technical Indicators (13)

rsi_14macdmacdSignalmacdHistogramstochKstochDwilliamsR_14sma_20sma_50sma_200ema_12ema_26atr_14

Momentum Features (7)

momentum_5momentum_10momentum_20rateOfChange_10rateOfChange_20priceChange_5priceChange_10

Volatility Features (3)

volatility_20volatility_50atr_14

Volume Features (5)

volumeChangevolumeChangePercentvolumeMean_20volumeStd_20volumeRatio_20

Rolling Statistics (14)

rollingMean_20rollingStd_20rollingMin_20rollingMax_20rollingMedian_20rollingMean_50rollingStd_50... and 7 more

Bollinger Bands (5)

bbUpperbbMiddlebbLowerbbWidthbbPercentB

Target Variables (6)

futureReturn_1futureReturn_5futureReturn_10futureDirection_1futureDirection_5futureDirection_10

Target variables for supervised learning (price prediction)

Usage Guide
How to use the exported data for machine learning

1. Python / scikit-learn

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier

# Load data
df = pd.read_csv('btcusd-ml-features-1h.csv')

# Separate features and target
X = df.drop(['timestamp', 'futureDirection_1'], axis=1)
y = df['futureDirection_1']

# Split data
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)

# Train model
model = RandomForestClassifier()
model.fit(X_train, y_train)

# Evaluate
accuracy = model.score(X_test, y_test)
print(f'Accuracy: {accuracy:.2%}')

2. TensorFlow / Keras

import pandas as pd
import tensorflow as tf
from tensorflow import keras

# Load data
df = pd.read_csv('btcusd-ml-features-1h.csv')

# Prepare data
X = df.drop(['timestamp', 'futureDirection_1'], axis=1).values
y = df['futureDirection_1'].values

# Build model
model = keras.Sequential([
    keras.layers.Dense(128, activation='relu', input_shape=(X.shape[1],)),
    keras.layers.Dropout(0.2),
    keras.layers.Dense(64, activation='relu'),
    keras.layers.Dense(1, activation='sigmoid')
])

model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
model.fit(X, y, epochs=50, batch_size=32, validation_split=0.2)

3. Feature Importance Analysis

import pandas as pd
from sklearn.ensemble import RandomForestClassifier
import matplotlib.pyplot as plt

# Load and train
df = pd.read_csv('btcusd-ml-features-1h.csv')
X = df.drop(['timestamp', 'futureDirection_1'], axis=1)
y = df['futureDirection_1']

model = RandomForestClassifier()
model.fit(X, y)

# Get feature importance
importance = pd.DataFrame({
    'feature': X.columns,
    'importance': model.feature_importances_
}).sort_values('importance', ascending=False)

print(importance.head(10))