{"id":29347,"date":"2024-10-27T16:17:59","date_gmt":"2024-10-27T16:17:59","guid":{"rendered":"http:\/\/atmokpo.com\/w\/?p=29347"},"modified":"2024-11-26T06:52:58","modified_gmt":"2024-11-26T06:52:58","slug":"%eb%a8%b8%ec%8b%a0%eb%9f%ac%eb%8b%9d-%eb%b0%8f-%eb%94%a5%eb%9f%ac%eb%8b%9d-%ec%95%8c%ea%b3%a0%eb%a6%ac%ec%a6%98-%ed%8a%b8%eb%a0%88%ec%9d%b4%eb%94%a9-%ed%80%80%eb%93%a4","status":"publish","type":"post","link":"https:\/\/atmokpo.com\/w\/29347\/","title":{"rendered":"\uba38\uc2e0\ub7ec\ub2dd \ubc0f \ub525\ub7ec\ub2dd \uc54c\uace0\ub9ac\uc998 \ud2b8\ub808\uc774\ub529, \ud000\ub4e4"},"content":{"rendered":"

<\/p>\n

\ucd5c\uadfc \uba87 \ub144 \uac04 \uae08\uc735 \uc2dc\uc7a5\uc5d0\uc11c \uc790\ub3d9\ub9e4\ub9e4 \uc2dc\uc2a4\ud15c\uc758 \uc911\uc694\uc131\uacfc \uc778\uae30\uac00 \ucee4\uc9c0\uace0 \uc788\uc2b5\ub2c8\ub2e4. \uc774\ub7ec\ud55c \uc2dc\uc2a4\ud15c\uc740 \ub370\uc774\ud130 \ubd84\uc11d\uacfc \uc54c\uace0\ub9ac\uc998\uc744 \ud1b5\ud574 \ud2b8\ub808\uc774\ub529 \uc804\ub7b5\uc744 \uc2e4\ud589\ud558\uc5ec \uc778\uac04 \ud2b8\ub808\uc774\ub354\uc758 \uac1c\uc785\uc744 \ucd5c\uc18c\ud654\ud558\uace0 \uc788\uc2b5\ub2c8\ub2e4. \ubcf8 \uae00\uc5d0\uc11c\ub294 \uba38\uc2e0\ub7ec\ub2dd\uacfc \ub525\ub7ec\ub2dd \uae30\ubc95\uc744 \ud65c\uc6a9\ud558\uc5ec \ud000\ud2b8 \ud22c\uc790 \uc54c\uace0\ub9ac\uc998\uc744 \uac1c\ubc1c\ud558\ub294 \ubc29\ubc95\uc5d0 \ub300\ud574 \uc790\uc138\ud788 \uc124\uba85\ud558\uaca0\uc2b5\ub2c8\ub2e4.<\/p>\n

1. \ud000\ud2b8 \ud2b8\ub808\uc774\ub529\uc758 \uc774\ud574<\/h2>\n

\ud000\ud2b8 \ud2b8\ub808\uc774\ub529\uc740 ‘Quantitative Trading’\uc758 \uc904\uc784\ub9d0\ub85c, \uc218\ud559\uc801 \ubaa8\ub378\uacfc \ub370\uc774\ud130 \ubd84\uc11d\uc744 \ud1b5\ud574 \ud22c\uc790 \uacb0\uc815\uc744 \ub0b4\ub9ac\ub294 \ubc29\ubc95\uc785\ub2c8\ub2e4. \ub192\uc740 \ub3c4\uad6c\uc640 \uae30\uc220\ub825\uc744 \ubc14\ud0d5\uc73c\ub85c \uc2dc\uc7a5\uc758 \ud750\ub984\uc5d0\uc11c \ud328\ud134\uacfc \uc2e0\ud638\ub97c \ucc3e\uc544\ub0b4\uc5b4 \ucd5c\uc801\uc758 \ub9e4\uc218 \ubc0f \ub9e4\ub3c4 \uc2dc\uc810\uc744 \uacb0\uc815\ud569\ub2c8\ub2e4. \ud000\ud2b8 \ud22c\uc790\uc5d0\uc11c \ub370\uc774\ud130\ub97c \ub2e4\ub8e8\ub294 \uc9c0\uc2dd\uacfc \uc54c\uace0\ub9ac\uc998 \uac1c\ubc1c \ub2a5\ub825\uc740 \ud544\uc218\uc801\uc778 \uc694\uc18c\uc785\ub2c8\ub2e4.<\/p>\n

2. \uba38\uc2e0\ub7ec\ub2dd\uacfc \ub525\ub7ec\ub2dd\uc758 \uae30\ubcf8 \uac1c\ub150<\/h2>\n

\uba38\uc2e0\ub7ec\ub2dd\uc740 \ub370\uc774\ud130\uc5d0\uc11c \ud328\ud134\uc744 \ud559\uc2b5\ud558\uc5ec \ubbf8\ub798\uc758 \uacb0\uacfc\ub97c \uc608\uce21\ud558\ub294 \uae30\uc220\uc785\ub2c8\ub2e4. \ub525\ub7ec\ub2dd\uc740 \uba38\uc2e0\ub7ec\ub2dd\uc758 \ud55c \ubd84\uc57c\ub85c, \uc778\uacf5\uc9c0\ub2a5 \uae30\uc220\uc744 \ud65c\uc6a9\ud558\uc5ec \ub300\ub7c9\uc758 \ub370\uc774\ud130\ub97c \ucc98\ub9ac\ud569\ub2c8\ub2e4. \uc774\ub7ec\ud55c \uae30\uc220\ub4e4\uc740 \ubcf5\uc7a1\ud55c \uae08\uc735 \uc2dc\uc7a5\uc758 \ub370\uc774\ud130\ub97c \ubd84\uc11d\ud558\uace0 \uc608\uce21\ud558\ub294 \ub370 \ub9e4\uc6b0 \uc720\uc6a9\ud569\ub2c8\ub2e4. \uba38\uc2e0\ub7ec\ub2dd \ubaa8\ub378\uc740 \uc8fc\uac00 \uc608\uce21, \uc2a4\ud338 \ud544\ud130\ub9c1, \ucd94\ucc9c \uc2dc\uc2a4\ud15c \ub4f1 \ub2e4\uc591\ud55c \ubd84\uc57c\uc5d0\uc11c \ud65c\uc6a9\ub418\uace0 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n

3. \uc54c\uace0\ub9ac\uc998 \ud2b8\ub808\uc774\ub529\uc758 \ud504\ub85c\uc138\uc2a4<\/h2>\n

3.1 \ub370\uc774\ud130 \uc218\uc9d1<\/h3>\n

\uccab \ubc88\uc9f8 \ub2e8\uacc4\ub294 \ud544\uc694\ud55c \ub370\uc774\ud130\ub97c \uc218\uc9d1\ud558\ub294 \uac83\uc785\ub2c8\ub2e4. \uc774\ub7ec\ud55c \ub370\uc774\ud130\ub294 \uc8fc\uac00, \uac70\ub798\ub7c9, \uae30\uc220\uc801 \uc9c0\ud45c, \uae30\uc5c5 \uc7ac\ubb34 \uc815\ubcf4 \ub4f1 \ub2e4\uc591\ud569\ub2c8\ub2e4. Python<\/code>\uc758 pandas<\/code> \ub77c\uc774\ube0c\ub7ec\ub9ac\ub97c \ud65c\uc6a9\ud558\uc5ec \ub370\uc774\ud130\ub97c \uc190\uc27d\uac8c \ucc98\ub9ac\ud558\uace0 \ubcc0\ud658\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n

3.2 \ub370\uc774\ud130 \uc804\ucc98\ub9ac<\/h3>\n

\uc218\uc9d1\ud55c \ub370\uc774\ud130\ub97c \ubd84\uc11d\ud558\uae30 \uc804\uc5d0 \uc804\ucc98\ub9ac \uacfc\uc815\uc774 \ud544\uc694\ud569\ub2c8\ub2e4. \uacb0\uce21\uac12 \ucc98\ub9ac, \uc774\uc0c1\uce58 \uc81c\uac70, \uc2a4\ucf00\uc77c\ub9c1 \ub4f1 \ub2e4\uc591\ud55c \uc804\ucc98\ub9ac \uae30\ubc95\uc744 \ud1b5\ud574 \ub370\uc774\ud130\uc758 \ud488\uc9c8\uc744 \ud5a5\uc0c1\uc2dc\ud0b5\ub2c8\ub2e4. \uc774 \ub2e8\uacc4\uc5d0\uc11c\ub294 numpy<\/code>\uc640 scikit-learn<\/code> \ub77c\uc774\ube0c\ub7ec\ub9ac\ub97c \uc8fc\ub85c \uc0ac\uc6a9\ud569\ub2c8\ub2e4.<\/p>\n

3.3 \ubaa8\ub378 \uc120\ud0dd<\/h3>\n

\uc804\ucc98\ub9ac\ub41c \ub370\uc774\ud130\ub97c \ubc14\ud0d5\uc73c\ub85c \ub2e4\uc591\ud55c \uba38\uc2e0\ub7ec\ub2dd \uc54c\uace0\ub9ac\uc998 \uc911\uc5d0\uc11c \uc801\ud569\ud55c \ubaa8\ub378\uc744 \uc120\ud0dd\ud569\ub2c8\ub2e4. \ud68c\uadc0 \ubd84\uc11d, \uc758\uc0ac \uacb0\uc815 \ub098\ubb34, \ub79c\ub364 \ud3ec\ub808\uc2a4\ud2b8, SVM, LSTM\uacfc \uac19\uc740 \uc54c\uace0\ub9ac\uc998\uc774 \uc790\uc8fc \uc0ac\uc6a9\ub429\ub2c8\ub2e4. \uac01 \uc54c\uace0\ub9ac\uc998\uc758 \ud2b9\uc131\uacfc \uc7a5\ub2e8\uc810\uc744 \uc798 \uc774\ud574\ud558\uace0 \uc120\ud0dd\ud558\ub294 \uac83\uc774 \uc911\uc694\ud569\ub2c8\ub2e4.<\/p>\n

3.4 \ubaa8\ub378 \ud559\uc2b5 \ubc0f \ud3c9\uac00<\/h3>\n

\uc120\ud0dd\ud55c \ubaa8\ub378\uc5d0 \ub370\uc774\ud130\ub97c \ud559\uc2b5\uc2dc\ud0a8 \ud6c4, \uc608\uce21 \uc131\ub2a5\uc744 \ud3c9\uac00\ud569\ub2c8\ub2e4. \ud3c9\uac00 \uae30\uc900\uc740 \uc77c\ubc18\uc801\uc73c\ub85c \uc815\ud655\ub3c4, \uc815\ubc00\ub3c4, \uc7ac\ud604\uc728, F1-score \ub4f1\uc758 \uc9c0\ud45c\ub97c \uc0ac\uc6a9\ud569\ub2c8\ub2e4. train_test_split<\/code>\uacfc \uac19\uc740 \ubc29\ubc95\uc744 \ud1b5\ud574 \ub370\uc774\ud130\ub97c \ud559\uc2b5\uc6a9\uacfc \ud14c\uc2a4\ud2b8\uc6a9\uc73c\ub85c \ub098\ub204\uc5b4 \uc131\ub2a5\uc744 \uce21\uc815\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n

3.5 \ud2b8\ub808\uc774\ub529 \uc804\ub7b5 \uad6c\ud604<\/h3>\n

\ubaa8\ub378\uc774 \uc608\uce21\ud55c \uacb0\uacfc\ub97c \uae30\ubc18\uc73c\ub85c \uc790\ub3d9\ub9e4\ub9e4 \uc804\ub7b5\uc744 \uc218\ub9bd\ud569\ub2c8\ub2e4. \ud2b9\uc815 \uc870\uac74\uc744 \ub9cc\uc871\ud560 \ub54c \ub9e4\uc218 \ub610\ub294 \ub9e4\ub3c4\ud558\ub294 \uaddc\uce59\uc744 \uc124\uc815\ud569\ub2c8\ub2e4. \ubc31\ud14c\uc2a4\ud305\uc744 \ud1b5\ud574 \uacfc\uac70 \ub370\uc774\ud130\uc5d0\uc11c \uc804\ub7b5\uc744 \uc801\uc6a9\ud574 \ubcf4\uace0, \uc218\uc775\ub960\uc744 \ubd84\uc11d\ud558\uc5ec \uc804\ub7b5\uc744 \ucd5c\uc801\ud654\ud569\ub2c8\ub2e4.<\/p>\n

3.6 \uc6b4\uc601 \ubc0f \ubaa8\ub2c8\ud130\ub9c1<\/h3>\n

\uc790\ub3d9\ub9e4\ub9e4 \uc2dc\uc2a4\ud15c\uc740 \ud55c \ubc88 \uad6c\ucd95\ud55c \ud6c4 \uc9c0\uc18d\uc801\uc73c\ub85c \uc6b4\uc601 \ubc0f \ubaa8\ub2c8\ud130\ub9c1\ud574\uc57c \ud569\ub2c8\ub2e4. \uc2dc\uc7a5\uc758 \ubcc0\ud654\uc5d0 \ub530\ub77c \ubaa8\ub378\uc758 \uc5c5\ub370\uc774\ud2b8\ub098 \uc7ac\ud559\uc2b5\uc774 \ud544\uc694\ud560 \uc218 \uc788\uc73c\uba70, \uc774\ub97c \ud1b5\ud574 \uc9c0\uc18d\uc801\uc778 \uc131\ub2a5 \uac1c\uc120\uc744 \ub3c4\ubaa8\ud569\ub2c8\ub2e4.<\/p>\n

4. \uc8fc\uc694 \uba38\uc2e0\ub7ec\ub2dd \ubc0f \ub525\ub7ec\ub2dd \uc54c\uace0\ub9ac\uc998<\/h2>\n

4.1 \uc120\ud615 \ud68c\uadc0(Linear Regression)<\/h3>\n

\uc120\ud615 \ud68c\uadc0\ub294 \uc885\uc18d \ubcc0\uc218\uc640 \ub3c5\ub9bd \ubcc0\uc218 \uac04\uc758 \uc120\ud615 \uad00\uacc4\ub97c \ubaa8\ub378\ub9c1\ud558\ub294 \ubc29\ubc95\uc785\ub2c8\ub2e4. \uc8fc\uc2dd \uac00\uaca9 \uc608\uce21\uacfc \uac19\uc774 \uc5f0\uc18d\uc801\uc778 \uac12\uc744 \ub2e4\ub8f0 \ub54c \uc720\uc6a9\ud558\uac8c \uc0ac\uc6a9\ub429\ub2c8\ub2e4.<\/p>\n

4.2 \uc758\uc0ac \uacb0\uc815 \ub098\ubb34(Decision Trees)<\/h3>\n

\uc758\uc0ac \uacb0\uc815 \ub098\ubb34\ub294 \ub370\uc774\ud130\ub97c \ubd84\ud560\ud558\uc5ec \uc758\uc0ac \uacb0\uc815\uc744 \uc2dc\uac01\uc801\uc73c\ub85c \ub098\ud0c0\ub0b4\ub294 \ubc29\ubc95\uc785\ub2c8\ub2e4. \uba85\ud655\ud55c \ud574\uc11d\uc774 \uac00\ub2a5\ud558\ub2e4\ub294 \uc7a5\uc810\uc774 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n

4.3 \ub79c\ub364 \ud3ec\ub808\uc2a4\ud2b8(Random Forest)<\/h3>\n

\ub79c\ub364 \ud3ec\ub808\uc2a4\ud2b8\ub294 \uc5ec\ub7ec \uac1c\uc758 \uc758\uc0ac \uacb0\uc815 \ub098\ubb34\ub97c \uacb0\ud569\ud558\uc5ec \uc608\uce21\uc758 \uc815\ud655\ub3c4\ub97c \ub192\uc774\ub294 \uc559\uc0c1\ube14 \ud559\uc2b5 \ubc29\ubc95\uc785\ub2c8\ub2e4. \uacfc\uc801\ud569 \ubb38\uc81c\ub97c \ud574\uacb0\ud558\ub294 \ub370 \ud6a8\uacfc\uc801\uc785\ub2c8\ub2e4.<\/p>\n

4.4 \uadf8\ub798\ub514\uc5b8\ud2b8 \ubd80\uc2a4\ud305(Gradient Boosting)<\/h3>\n

\uadf8\ub798\ub514\uc5b8\ud2b8 \ubd80\uc2a4\ud305\uc740 \uc57d\ud55c \uc608\uce21\uae30\ub97c \uacb0\ud569\ud558\ub294 \ubc29\ubc95\uc73c\ub85c, \uc608\uce21 \uc131\ub2a5\uc774 \ub9e4\uc6b0 \ub192\uc2b5\ub2c8\ub2e4. XGBoost\uc640 LightGBM \uac19\uc740 \ub77c\uc774\ube0c\ub7ec\ub9ac\uc5d0\uc11c \uad6c\ud604\ub418\uc5b4 \uc0ac\uc6a9\ub429\ub2c8\ub2e4.<\/p>\n

4.5 LSTM(Long Short-Term Memory)<\/h3>\n

LSTM\uc740 \uc2dc\uacc4\uc5f4 \ub370\uc774\ud130 \uc608\uce21\uc5d0 \ud2b9\ud654\ub41c \ub525\ub7ec\ub2dd \ubaa8\ub378\ub85c, \uc8fc\uac00 \uc608\uce21\uc5d0\uc11c \uc8fc\ub85c \uc0ac\uc6a9\ub429\ub2c8\ub2e4. \uacfc\uac70\uc758 \uc815\ubcf4\ub97c \uae30\uc5b5\ud558\uba74\uc11c\ub3c4 \ubd88\ud544\uc694\ud55c \uc815\ubcf4\ub97c \uc78a\uc5b4\ubc84\ub9ac\ub294 \ub2a5\ub825\uc774 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n

5. \ud30c\uc774\uc36c\uc744 \uc774\uc6a9\ud55c \ud000\ud2b8 \ud2b8\ub808\uc774\ub529 \uc608\uc81c<\/h2>\n

\uc5ec\uae30\uc11c\ub294 \uac04\ub2e8\ud55c \ud000\ud2b8 \ud2b8\ub808\uc774\ub529 \uc54c\uace0\ub9ac\uc998\uc744 \ud30c\uc774\uc36c\uc73c\ub85c \uad6c\ud604\ud558\ub294 \uc608\uc81c\ub97c \uc18c\uac1c\ud558\uaca0\uc2b5\ub2c8\ub2e4. \uc544\ub798\ub294 \uacfc\uac70 \uc8fc\uac00 \ub370\uc774\ud130\ub97c \uae30\ubc18\uc73c\ub85c \uc774\ub3d9 \ud3c9\uade0 \uad50\ucc28 \uc804\ub7b5\uc744 \uad6c\ud604\ud558\ub294 \ucf54\ub4dc\uc785\ub2c8\ub2e4.<\/p>\n

import pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom sklearn.model_selection import train_test_split\n\n# \ub370\uc774\ud130 \ubd88\ub7ec\uc624\uae30\ndata = pd.read_csv('historical_stock_prices.csv')\n\n# \uc774\ub3d9 \ud3c9\uade0 \uacc4\uc0b0\ndata['SMA_30'] = data['Close'].rolling(window=30).mean()\ndata['SMA_100'] = data['Close'].rolling(window=100).mean()\n\n# \ub9e4\uc218 \ubc0f \ub9e4\ub3c4 \uc2e0\ud638 \uc0dd\uc131\ndata['Signal'] = 0\ndata['Signal'][30:] = np.where(data['SMA_30'][30:] > data['SMA_100'][30:], 1, 0)\n\n# \ud3ec\ud2b8\ud3f4\ub9ac\uc624 \uc131\uacfc \ud3c9\uac00\ndata['Strategy'] = data['Signal'].shift(1) * data['Close'].pct_change()\ndata['Cumulative Strategy'] = (1 + data['Strategy']).cumprod()\n\n# \uc2dc\uac01\ud654\nplt.figure(figsize=(12, 6))\nplt.plot(data['Cumulative Strategy'], label='Cumulative Strategy', color='g')\nplt.plot(data['Close'].pct_change().cumsum(), label='Cumulative Market', color='r')\nplt.title('Strategy vs Market Performance')\nplt.legend()\nplt.show()<\/code><\/pre>\n
6. \uacb0\ub860<\/h2>\n
\uba38\uc2e0\ub7ec\ub2dd\uacfc \ub525\ub7ec\ub2dd\uc744 \ud65c\uc6a9\ud55c \ud000\ud2b8 \ud2b8\ub808\uc774\ub529\uc740 \ub370\uc774\ud130 \ubd84\uc11d\uc744 \ud1b5\ud55c \uc2dc\uc7a5 \uc608\uce21\uc758 \uc0c8\ub85c\uc6b4 \ud328\ub7ec\ub2e4\uc784\uc744 \uc81c\uc2dc\ud569\ub2c8\ub2e4. \ud558\uc9c0\ub9cc \uc774\ub97c \uc131\uacf5\uc801\uc73c\ub85c \uad6c\ud604\ud558\uae30 \uc704\ud574\uc11c\ub294 \ucda9\ubd84\ud55c \ub370\uc774\ud130, \uc801\uc808\ud55c \uc54c\uace0\ub9ac\uc998 \uc120\ud0dd, \uadf8\ub9ac\uace0 \uc9c0\uc18d\uc801\uc778 \ubaa8\ub2c8\ud130\ub9c1\uc774 \uc694\uad6c\ub429\ub2c8\ub2e4. \uc774 \uae00\uc744 \ud1b5\ud574 \ud000\ud2b8 \ud22c\uc790\uc5d0 \ub300\ud55c \uae30\ucd08 \uc9c0\uc2dd\uc744 \uc313\uc558\ub2e4\uba74, \uc2e4\uc81c \ud504\ub85c\uc81d\ud2b8\uc5d0 \ub3c4\uc804\ud574 \ubcf4\uae30\ub97c \uad8c\uc7a5\ud569\ub2c8\ub2e4<\/p>\n
7. \ucc38\uace0 \uc790\ub8cc<\/h2>\n