This tutorial walks you through building a true 6-factor Bitcoin trading strategy from scratch using Python. By leveraging classic technical indicators\u2014EMA, MACD, RSI, KDJ, CCI, and OBV\u2014we construct a signal classification model that outputs Buy, Sell, or Hold decisions.<\/p>\n\n\n\n
btc_data = pd.read_csv(\"btc_data.csv\", parse_dates=['Open time'])\nbtc_data.set_index('Open time', inplace=True)\nbtc_data.rename(columns=lambda x: x.lower(), inplace=True)<\/code><\/pre>\n\n\n\nWe load 15-minute interval BTC price data and set the timestamp as the index.<\/p>\n\n\n\n
Step 2: Add Technical Indicators<\/h2>\n\n\n\n
Using the pandas_ta<\/code> library, we calculate the following indicators:<\/p>\n\n\n\n\n- EMA<\/strong>: 6, 18, and 60-period Exponential Moving Averages<\/li>\n\n\n\n
- MACD<\/strong> & Signal Line<\/li>\n\n\n\n
- RSI<\/strong> (14-period)<\/li>\n\n\n\n
- CCI<\/strong> (14-period Commodity Channel Index)<\/li>\n\n\n\n
- KDJ<\/strong> (Stochastic Oscillator)<\/li>\n\n\n\n
- OBV<\/strong> (On-Balance Volume)<\/li>\n<\/ul>\n\n\n\n
import pandas_ta as ta\n\ndf['EMA_6'] = ta.ema(df['close'], length=6)\ndf['EMA_18'] = ta.ema(df['close'], length=18)\n# ...\ndf['OBV'] = ta.obv(df['close'], df['volume'])\ndf.dropna(inplace=True)<\/code><\/pre>\n\n\n\nEach factor represents a different dimension of market behavior\u2014momentum, volume flow, or sentiment.<\/p>\n\n\n\n
Step 3: Price Prediction Model<\/h2>\n\n\n\n
We use the technical indicators to predict the next period\u2019s closing price:<\/p>\n\n\n\n
X = df[[\"EMA_6\", \"EMA_18\", ..., \"OBV\"]]\ny = df['close'].shift(-1)<\/code><\/pre>\n\n\n\nTrain a regression model (e.g., linear regression):<\/p>\n\n\n\n
from sklearn.linear_model import LinearRegression\n\nmodel = LinearRegression()\nmodel.fit(X_train, y_train)<\/code><\/pre>\n\n\n\nYou can include the predicted price (Predicted_Close<\/code>) as an additional feature in the classification step.<\/p>\n\n\n\nStep 4: Signal Classification Model (Buy\/Sell\/Hold)<\/h2>\n\n\n\n
We define trading signals based on the following rule-based logic:<\/p>\n\n\n\n
y = np.where(\n (EMA_6 > EMA_18) & (MACD > MACD_signal) & (RSI > 30) &\n (K > D) & (CCI > 100) & (OBV > OBV.shift(1)), 1,\n np.where(\n (EMA_6 < EMA_18) & (MACD < MACD_signal) & (RSI < 70) &\n (K < D) & (CCI < -100) & (OBV < OBV.shift(1)), -1, 0\n )\n)<\/code><\/pre>\n\n\n\nThen, train a classifier to predict these Buy\/Sell\/Hold labels:<\/p>\n\n\n\n
from sklearn.ensemble import RandomForestClassifier\n\nmodel = RandomForestClassifier(max_depth=5)\nmodel.fit(X_train, y_train)<\/code><\/pre>\n\n\n\nStep 5: Visualizing Strategy Performance<\/h2>\n\n\n\n
Using Plotly, we visualize:<\/p>\n\n\n\n
\n- Actual vs. Predicted price<\/li>\n\n\n\n
- Buy signals (green triangle)<\/li>\n\n\n\n
- Sell signals (red inverted triangle)<\/li>\n\n\n\n
- Hold signals (yellow dots)<\/li>\n<\/ul>\n\n\n\n
fig.add_trace(go.Scatter(..., name='Buy'))\nfig.add_trace(go.Scatter(..., name='Sell'))\nfig.add_trace(go.Scatter(..., name='Hold'))<\/code><\/pre>\n\n\n\nSummary<\/h2>\n\n\n\n\n- \u2705 Technical factors based on classic indicators: MACD, KDJ, OBV, etc.<\/li>\n\n\n\n
- \ud83d\udd04 Labels generated using combined conditions (rule-based logic)<\/li>\n\n\n\n
- \ud83e\udd16 Classification powered by machine learning (Random Forest)<\/li>\n\n\n\n
- \ud83d\udcc8 Visual outputs help evaluate strategy performance and logic<\/li>\n<\/ul>\n\n\n\n
Download & Connect<\/h2>\n\n\n\n
The complete code and dataset will be available on GitHub soon.<\/p>\n\n\n\n
<\/p>\n","protected":false},"excerpt":{"rendered":"
This tutorial walks you through building a true 6-factor Bitcoin trading strategy from scratch using Python. By leveraging classic technical indicators\u2014EMA, MACD, RSI, KDJ, CCI, and OBV\u2014we construct a signal classification model that outputs Buy, Sell, or Hold decisions. Step 1: Load Bitcoin Data We load 15-minute interval BTC price data and set the timestamp […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-59","post","type-post","status-publish","format-standard","hentry","category-tutorial"],"_links":{"self":[{"href":"http:\/\/www.ashwang.net\/index.php\/wp-json\/wp\/v2\/posts\/59","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/www.ashwang.net\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/www.ashwang.net\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/www.ashwang.net\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/www.ashwang.net\/index.php\/wp-json\/wp\/v2\/comments?post=59"}],"version-history":[{"count":1,"href":"http:\/\/www.ashwang.net\/index.php\/wp-json\/wp\/v2\/posts\/59\/revisions"}],"predecessor-version":[{"id":60,"href":"http:\/\/www.ashwang.net\/index.php\/wp-json\/wp\/v2\/posts\/59\/revisions\/60"}],"wp:attachment":[{"href":"http:\/\/www.ashwang.net\/index.php\/wp-json\/wp\/v2\/media?parent=59"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www.ashwang.net\/index.php\/wp-json\/wp\/v2\/categories?post=59"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www.ashwang.net\/index.php\/wp-json\/wp\/v2\/tags?post=59"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}