\n \ub370\uc774\ud130 \uae30\ubc18\uc758 \ud2b8\ub808\uc774\ub529 \uc804\ub7b5\uc740 \ucd5c\uadfc \uba87 \ub144\uac04 \uae09\uaca9\ud55c \ubc1c\uc804\uc744 \uc774\ub8e8\uc5c8\uc2b5\ub2c8\ub2e4. \ud2b9\ud788 \uba38\uc2e0\ub7ec\ub2dd\uacfc \ub525\ub7ec\ub2dd \uae30\ubc95\ub4e4\uc740 \uae08\uc735 \ub370\uc774\ud130\uc758 \ubcf5\uc7a1\uc131\uc744 \uc774\ud574\ud558\uace0 \uc720\uc6a9\ud55c \uc815\ubcf4\ub97c \ucd94\ucd9c\ud558\ub294 \ub370 \ud070 \ub3c4\uc6c0\uc744 \uc8fc\uace0 \uc788\uc2b5\ub2c8\ub2e4. \ubcf8 \uae00\uc5d0\uc11c\ub294 \uba38\uc2e0\ub7ec\ub2dd \uae30\ubc95 \uc911 \ud558\ub098\uc778 \ub79c\ub364 \ud3ec\ub808\uc2a4\ud2b8(Random Forest)\ub97c \uc774\uc6a9\ud55c \uc54c\uace0\ub9ac\uc998 \ud2b8\ub808\uc774\ub529\uc5d0\uc11c\uc758 \ud2b9\uc131 \uc911\uc694\ub3c4(Feature Importance)\uc5d0 \ub300\ud574 \uae4a\uc774 \uc788\uac8c \ub17c\uc758\ud558\uace0\uc790 \ud569\ub2c8\ub2e4.\n <\/p>\n
\n \uba38\uc2e0\ub7ec\ub2dd\uc740 \ub370\uc774\ud130\ub97c \uae30\ubc18\uc73c\ub85c \ud559\uc2b5\ud558\uace0 \uc608\uce21\ud558\ub294 \uc54c\uace0\ub9ac\uc998\uc758 \uc9d1\ud569\uc785\ub2c8\ub2e4. \uc774 \uacfc\uc815\uc5d0\uc11c \ub2e4\uc591\ud55c \ud2b9\uc131\uc744 \uace0\ub824\ud558\uc5ec \ubaa8\ub378\uc744 \ud559\uc2b5\ud558\uace0, \uc774\ub97c \ud1b5\ud574 \uc0c8\ub85c\uc6b4 \ub370\uc774\ud130\uc5d0 \ub300\ud55c \uc608\uce21\uc744 \uc218\ud589\ud569\ub2c8\ub2e4. \ub525\ub7ec\ub2dd\uc740 \uba38\uc2e0\ub7ec\ub2dd\uc758 \ud55c \ubd84\uc57c\ub85c, \uc778\uacf5\uc2e0\uacbd\ub9dd\uc744 \ud65c\uc6a9\ud558\uc5ec \ub354\uc6b1 \ubcf5\uc7a1\ud55c \ub370\uc774\ud130 \ud328\ud134\uc744 \ud559\uc2b5\ud569\ub2c8\ub2e4. \uc774 \ub450 \uac00\uc9c0 \ubc29\ubc95\ub860\uc740 \uae08\uc735 \uc2dc\uc7a5\uc5d0\uc11c \uc790\ub3d9\ub9e4\ub9e4\ub97c \uc704\ud574 \ub110\ub9ac \uc0ac\uc6a9\ub429\ub2c8\ub2e4.\n <\/p>\n
\n \ub79c\ub364 \ud3ec\ub808\uc2a4\ud2b8\ub294 \uc758\uc0ac\uacb0\uc815 \ub098\ubb34(Decision Tree) \uae30\ubc18\uc758 \uc559\uc0c1\ube14 \ud559\uc2b5 \ubc29\ubc95\uc785\ub2c8\ub2e4. \uc5ec\ub7ec \uac1c\uc758 \uacb0\uc815 \ud2b8\ub9ac\ub97c \uc0dd\uc131\ud558\uace0, \uc774\ub4e4\uc758 \uc608\uce21\uc744 \ud3c9\uade0\ud558\uc5ec \ucd5c\uc885 \uc608\uce21\uc744 \ub0b4\ub9bd\ub2c8\ub2e4. \uc774 \uacfc\uc815\uc5d0\uc11c \uac01 \ud2b8\ub9ac\ub294 \uc11c\ub85c \ub2e4\ub978 \uc0d8\ud50c\uacfc \ud2b9\uc131\uc744 \ubc14\ud0d5\uc73c\ub85c \uc0dd\uc131\ub418\ubbc0\ub85c \uacfc\uc801\ud569(overfitting)\uc744 \uc904\uc77c \uc218 \uc788\uc2b5\ub2c8\ub2e4. \ub79c\ub364 \ud3ec\ub808\uc2a4\ud2b8\ub294 \ud2b9\ud788 \uae08\uc735 \ub370\uc774\ud130\uc640 \uac19\uc740 \uace0\ucc28\uc6d0\uc758 \ub370\uc774\ud130\uc5d0 \ub9e4\uc6b0 \uc720\uc6a9\ud55c \uc131\ub2a5\uc744 \ubcf4\uc785\ub2c8\ub2e4.\n <\/p>\n
\n \ub79c\ub364 \ud3ec\ub808\uc2a4\ud2b8\uc758 \uc791\ub3d9 \uacfc\uc815\uc740 \ub2e4\uc74c\uacfc \uac19\uc2b5\ub2c8\ub2e4:<\/p>\n
\n \ud2b9\uc131 \uc911\uc694\ub3c4\ub294 \ubaa8\ub378\uc774 \uc608\uce21\uc744 \uc218\ud589\ud560 \ub54c \uac01 \ud2b9\uc131\uc774 \uc5bc\ub9c8\ub098 \uc911\uc694\ud55c\uc9c0\ub97c \ub098\ud0c0\ub0b4\ub294 \uc9c0\ud45c\uc785\ub2c8\ub2e4. \ub79c\ub364 \ud3ec\ub808\uc2a4\ud2b8\ub294 \ud2b9\uc131 \uc911\uc694\ub3c4\ub97c \ud3c9\uac00\ud558\uae30 \uc704\ud574 \uc8fc\ub85c \ub450 \uac00\uc9c0 \ubc29\ubc95\uc744 \uc0ac\uc6a9\ud569\ub2c8\ub2e4:<\/p>\n
\n \ubd88\uc21c\ub3c4 \uac10\uc18c\ub294 \uac01 \ud2b9\uc131\uc744 \uc0ac\uc6a9\ud574 \ub178\ub4dc\ub97c \ubd84\ud560\ud560 \ub54c\uc758 \ubd88\uc21c\ub3c4 \ubcc0\ud654\ub7c9\uc744 \uae30\ub85d\ud569\ub2c8\ub2e4. \ub192\uc740 \ubd88\uc21c\ub3c4 \uac10\uc18c\uac12\uc744 \uac00\uc9c4 \ud2b9\uc131\uc77c\uc218\ub85d \ubaa8\ub378\uc758 \uc608\uce21\uc5d0 \ub354 \ud070 \uae30\uc5ec\ub97c \ud569\ub2c8\ub2e4. \uc774\ub294 \ubaa8\ub378\uc758 \ud2b8\ub9ac\uac00 \uac01 \ud2b9\uc131\uc5d0 \ub300\ud574 \uc5bc\ub9c8\ub098 \ud6a8\uc728\uc801\uc73c\ub85c \uc608\uce21\ud558\ub294\uc9c0\ub97c \uce21\uc815\ud558\uac8c \ub429\ub2c8\ub2e4.\n <\/p>\n
\n \ud37c\ubba4\ud14c\uc774\uc158 \uc911\uc694\ub3c4\ub294 \ubaa8\ub378\uc744 \ud559\uc2b5\ud55c \ud6c4\uc5d0 \uac01 \ud2b9\uc131\uc758 \uac12\uc744 \ubb34\uc791\uc704\ub85c \uc11e\uc5b4 \uc608\uce21 \uc131\ub2a5\uc758 \ubcc0\ud654\ub97c \uce21\uc815\ud569\ub2c8\ub2e4. \uc608\uce21 \uc131\ub2a5\uc774 \ud06c\uac8c \uac10\uc18c\ud55c\ub2e4\uba74 \ud574\ub2f9 \ud2b9\uc131\uc774 \ubaa8\ub378\uc5d0\uc11c \uc911\uc694\ud55c \uc5ed\ud560\uc744 \ud558\uace0 \uc788\ub2e4\ub294 \uac83\uc744 \uc758\ubbf8\ud569\ub2c8\ub2e4. \uc774\ub294 \uac01 \ud2b9\uc131\uc774 \ub3c5\ub9bd\uc801\uc73c\ub85c \uc131\uacfc\uc5d0 \ubbf8\uce58\ub294 \uc601\ud5a5\uc744 \ud3c9\uac00\ud560 \uc218 \uc788\ub294 \uc7a5\uc810\uc774 \uc788\uc2b5\ub2c8\ub2e4.\n <\/p>\n
\n \ud2b9\uc131 \uc911\uc694\ub3c4\ub97c \uc774\ud574\ud558\ub294 \uac83\uc740 \uc54c\uace0\ub9ac\uc998 \ud2b8\ub808\uc774\ub529\uc758 \uc131\uacf5\uc5d0 \uc911\uc694\ud55c \uc694\uc18c\uc785\ub2c8\ub2e4. \uadf8 \uc774\uc720\ub294:<\/p>\n
\n \ub79c\ub364 \ud3ec\ub808\uc2a4\ud2b8 \ubaa8\ub378\uc744 \uad6c\ucd95\ud558\uae30 \uc704\ud574\uc11c\ub294 \uc131\uacfc \uc9c0\ud45c\ub97c \uc815\uc758\ud558\uace0, \ud2b9\uc131\uc744 \uc120\uc815\ud558\uba70, \ubaa8\ub378\uc744 \ud559\uc2b5\ud558\ub294 \uacfc\uc815\uc774 \ud544\uc694\ud569\ub2c8\ub2e4. Python\uc758 Scikit-learn \ub77c\uc774\ube0c\ub7ec\ub9ac\ub97c \ud65c\uc6a9\ud558\uc5ec \ubaa8\ub378\uc744 \uad6c\ucd95\ud558\ub294 \ubc29\ubc95\uc744 \uc124\uba85\ud569\ub2c8\ub2e4.\n <\/p>\n
\n \uba3c\uc800, \ubaa8\ub378\uc5d0 \uc0ac\uc6a9\ud560 \ub370\uc774\ud130\ub97c \uc900\ube44\ud574\uc57c \ud569\ub2c8\ub2e4. \uc774 \uc608\uc2dc\uc5d0\uc11c\ub294 Yahoo Finance API\ub97c \uc774\uc6a9\ud558\uc5ec \uc8fc\uc2dd \ub370\uc774\ud130\ub97c \uc218\uc9d1\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.\n <\/p>\n
\n \n import pandas as pd\n import yfinance as yf\n\n # \ub370\uc774\ud130 \uc218\uc9d1\n data = yf.download('AAPL', start='2015-01-01', end='2021-01-01')\n data['Return'] = data['Adj Close'].pct_change()\n data.dropna(inplace=True)\n <\/code>\n <\/pre>\n5.2 \ud2b9\uc131 \uad6c\ucd95<\/h3>\n
\n \uc608\uce21\uc5d0 \ud544\uc694\ud55c \ub2e4\uc591\ud55c \ud2b9\uc131\uc744 \uad6c\ucd95\ud569\ub2c8\ub2e4. \uc608\ub97c \ub4e4\uc5b4 \uc774\ub3d9 \ud3c9\uade0, \uc0c1\ub300 \uac15\ub3c4 \uc9c0\uc218, MACD \ub4f1\uc744 \ud3ec\ud568\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.\n <\/p>\n
\n \n # \uc774\ub3d9 \ud3c9\uade0 \ud2b9\uc131\n data['SMA'] = data['Adj Close'].rolling(window=20).mean()\n\n # \uc0c1\ub300 \uac15\ub3c4 \uc9c0\uc218\n delta = data['Adj Close'].diff()\n gain = (delta.where(delta > 0, 0)).rolling(window=14).mean()\n loss = (-delta.where(delta < 0, 0)).rolling(window=14).mean()\n rs = gain \/ loss\n data['RSI'] = 100 - (100 \/ (1 + rs))\n <\/code>\n <\/pre>\n5.3 \ub79c\ub364 \ud3ec\ub808\uc2a4\ud2b8 \ubaa8\ub378 \ud559\uc2b5<\/h3>\n
\n \uc774\uc81c \ud2b9\uc131\uc744 \uc774\uc6a9\ud558\uc5ec \ub79c\ub364 \ud3ec\ub808\uc2a4\ud2b8 \ubaa8\ub378\uc744 \ud559\uc2b5\ud560 \uc900\ube44\uac00 \ub418\uc5c8\uc2b5\ub2c8\ub2e4.\n <\/p>\n
\n \n from sklearn.ensemble import RandomForestClassifier\n from sklearn.model_selection import train_test_split\n from sklearn.metrics import classification_report\n\n # \ud2b9\uc131\uacfc \ud0c0\uac9f \ubcc0\uc218 \uc124\uc815\n features = data[['SMA', 'RSI']]\n target = (data['Return'] > 0).astype(int)\n\n X_train, X_test, y_train, y_test = train_test_split(features, target, test_size=0.2, random_state=42)\n\n # \ubaa8\ub378 \ud559\uc2b5\n model = RandomForestClassifier(n_estimators=100, random_state=42)\n model.fit(X_train, y_train)\n\n # \uc608\uce21 \ubc0f \ud3c9\uac00\n predictions = model.predict(X_test)\n print(classification_report(y_test, predictions))\n <\/code>\n <\/pre>\n5.4 \ud2b9\uc131 \uc911\uc694\ub3c4 \ud3c9\uac00<\/h3>\n
\n \ubaa8\ub378 \ud559\uc2b5 \ud6c4, \ud2b9\uc131 \uc911\uc694\ub3c4\ub97c \ud3c9\uac00\ud558\uc5ec \uc911\uc694\ud55c \ud2b9\uc131\uc744 \ubd84\uc11d\ud569\ub2c8\ub2e4.\n <\/p>\n
\n \n import matplotlib.pyplot as plt\n import numpy as np\n\n # \ud2b9\uc131 \uc911\uc694\ub3c4 \uc2dc\uac01\ud654\n importances = model.feature_importances_\n indices = np.argsort(importances)[::-1]\n\n plt.title('Feature Importances')\n plt.bar(range(len(importances)), importances[indices], align='center')\n plt.xticks(range(len(importances)), np.array(features.columns)[indices], rotation=90)\n plt.xlim([-1, len(importances)])\n plt.show()\n <\/code>\n <\/pre>\n6. \uacb0\ub860<\/h2>\n
\n \ub79c\ub364 \ud3ec\ub808\uc2a4\ud2b8 \ubaa8\ub378\uc744 \uc774\uc6a9\ud55c \ud2b9\uc131 \uc911\uc694\ub3c4 \ubd84\uc11d\uc740 \uc54c\uace0\ub9ac\uc998 \ud2b8\ub808\uc774\ub529\uc5d0\uc11c \ub9e4\uc6b0 \uc911\uc694\ud55c \uc694\uc18c\uc785\ub2c8\ub2e4. \uc774\ub97c \ud1b5\ud574 \uc6b0\ub9ac\ub294 \uc5b4\ub5a4 \ud2b9\uc131\uc774 \ubaa8\ub378\uc758 \uc608\uce21\uc5d0 \uac00\uc7a5 \ud06c\uac8c \uae30\uc5ec\ud558\ub294\uc9c0\ub97c \ud30c\uc545\ud558\uace0, \ubcf4\ub2e4 \ud6a8\uacfc\uc801\uc778 \ud2b8\ub808\uc774\ub529 \uc804\ub7b5\uc744 \uc218\ub9bd\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4. \uba38\uc2e0\ub7ec\ub2dd\uacfc \ub525\ub7ec\ub2dd\uc758 \uc9c0\uc18d\uc801\uc778 \ubc1c\uc804\uacfc \ud568\uaed8, \uc774\ub7ec\ud55c \uae30\ubc95\ub4e4\uc740 \uc55e\uc73c\ub85c\ub3c4 \ub354 \ub9ce\uc740 \ud22c\uc790\uc790\ub4e4\uc5d0\uac8c \uc601\ud5a5\uc744 \ubbf8\uce60 \uac83\uc785\ub2c8\ub2e4.\n <\/p>\n
\ucc38\uace0 \ubb38\ud5cc<\/h2>\n