\ucd5c\uadfc \uba87 \ub144\uac04 \uba38\uc2e0\ub7ec\ub2dd \ubc0f \ub525\ub7ec\ub2dd \uae30\uc220\uc774 \uae09\uc18d\ud788 \ubc1c\uc804\ud558\uba74\uc11c \uae08\uc735 \ubd84\uc57c\uc5d0\uc11c\ub3c4 \uc774\ub4e4\uc744 \ud65c\uc6a9\ud55c \uc790\ub3d9 \ub9e4\ub9e4 \uc54c\uace0\ub9ac\uc998\uc774 \ub2e4\uc591\ud55c \uc5f0\uad6c \ubc0f \uc2e4\ud5d8 \ub300\uc0c1\uc73c\ub85c \ub5a0\uc624\ub974\uace0 \uc788\uc2b5\ub2c8\ub2e4. \ubcf8 \uac15\uc88c\uc5d0\uc11c\ub294 \uba38\uc2e0\ub7ec\ub2dd\uacfc \ub525\ub7ec\ub2dd\uc744 \ud65c\uc6a9\ud558\uc5ec \uc54c\uace0\ub9ac\uc998 \uac70\ub798\ub97c \uad6c\ud604\ud558\ub294 \ubc29\ubc95, \ud2b9\ud788 \uc2ec\uce35 \uc21c\ud658 \uc2e0\uacbd\ub9dd(Deep Recurrent Neural Network, RNN)\uc758 \uc124\uacc4 \ubc0f \uad6c\ud604 \ubc29\ubc95\uc744 \uc0c1\uc138\ud788 \uc54c\uc544\ubcf4\uaca0\uc2b5\ub2c8\ub2e4.<\/p>\n
\uc54c\uace0\ub9ac\uc998 \ud2b8\ub808\uc774\ub529\uc740 \ucef4\ud4e8\ud130 \ud504\ub85c\uadf8\ub7a8\uc744 \uc0ac\uc6a9\ud558\uc5ec \ubbf8\ub9ac \uc815\uc758\ub41c \uc870\uac74\uc5d0 \ub530\ub77c \uae08\uc735 \uc790\uc0b0\uc744 \uc790\ub3d9\uc73c\ub85c \uac70\ub798\ud558\ub294 \ubc29\ubc95\uc785\ub2c8\ub2e4. \uc54c\uace0\ub9ac\uc998\uc740 \uc2dc\uc7a5 \ub370\uc774\ud130\ub97c \uc218\uc9d1\ud558\uace0 \ubd84\uc11d\ud558\uc5ec \uc801\uc808\ud55c \uc2dc\uc810\uc5d0 \uac70\ub798\ub97c \uc2e4\ud589\ud558\uac8c \ub429\ub2c8\ub2e4. \uba38\uc2e0\ub7ec\ub2dd\uacfc \ub525\ub7ec\ub2dd\uc744 \ud65c\uc6a9\ud55c \uc54c\uace0\ub9ac\uc998 \ud2b8\ub808\uc774\ub529\uc740 \ub370\uc774\ud130 \uae30\ubc18\uc758 \uc758\uc0ac\uacb0\uc815\uc744 \uac00\ub2a5\ud558\uac8c \ud558\uc5ec, \ub354 \ub098\uc740 \ud22c\uc790 \uc131\uacfc\ub97c \uae30\ub300\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n
\uba38\uc2e0\ub7ec\ub2dd\uc740 \ub370\uc774\ud130\ub85c\ubd80\ud130 \ud559\uc2b5\ud558\uc5ec \uc608\uce21\ud558\ub294 \ubaa8\ub378\uc744 \ub9cc\ub4dc\ub294 \uae30\uc220\uc785\ub2c8\ub2e4. \uc8fc\ub85c \ub370\uc774\ud130\uc758 \ud328\ud134\uc744 \ubd84\uc11d\ud558\uc5ec \ubbf8\ub798\uc5d0 \ub300\ud55c \uc608\uce21\uc744 \uc218\ud589\ud569\ub2c8\ub2e4. \uba38\uc2e0\ub7ec\ub2dd\uc740 \ud06c\uac8c \uc9c0\ub3c4\ud559\uc2b5, \ube44\uc9c0\ub3c4\ud559\uc2b5, \uac15\ud654\ud559\uc2b5\uc73c\ub85c \uad6c\ubd84\ub429\ub2c8\ub2e4.<\/p>\n
\ub525\ub7ec\ub2dd\uc740 \uc778\uacf5\uc2e0\uacbd\ub9dd\uc758 \uc2ec\uce35 \uad6c\uc870\ub97c \ud1b5\ud55c \ud559\uc2b5 \ubc29\ubc95\uc73c\ub85c, \ud2b9\ud788 \ube44\uc815\ud615 \ub370\uc774\ud130(\uc608: \uc774\ubbf8\uc9c0, \ud14d\uc2a4\ud2b8)\uc5d0 \uac15\ud55c \uc131\ub2a5\uc744 \ubc1c\ud718\ud569\ub2c8\ub2e4. \ub525\ub7ec\ub2dd \ubaa8\ub378\uc740 \uc5ec\ub7ec \uce35\uc758 \ub274\ub7f0\uc73c\ub85c \uad6c\uc131\ub418\uc5b4 \uc788\uc73c\uba70, \uac01 \uce35\uc744 \ud1b5\uacfc\ud558\uba74\uc11c \uc785\ub825 \ub370\uc774\ud130\uc758 \ud2b9\uc9d5\uc744 \uc810\uc9c4\uc801\uc73c\ub85c \ucd94\ucd9c\ud569\ub2c8\ub2e4.<\/p>\n
\uc21c\ud658 \uc2e0\uacbd\ub9dd(RNN)\uc740 \uc2dc\ud000\uc2a4 \ub370\uc774\ud130\ub97c \ucc98\ub9ac\ud558\ub294 \ub370 \uc801\ud569\ud55c \uad6c\uc870\ub85c, \uc774\uc804 \uc0c1\ud0dc\uc758 \uc815\ubcf4\ub97c \ub2e4\uc74c \uc0c1\ud0dc\ub85c \uc804\ub2ec\ud569\ub2c8\ub2e4. \uc2ec\uce35 RNN\uc740 \uc774\ub7ec\ud55c RNN \uad6c\uc870\ub97c \uc5ec\ub7ec \uce35\uc73c\ub85c \uc313\uc544 \ub354 \ubcf5\uc7a1\ud55c \ud328\ud134\uc744 \ud559\uc2b5\ud560 \uc218 \uc788\uac8c \ud574\uc90d\ub2c8\ub2e4. \uc774\ub294 \uc2dc\uacc4\uc5f4 \ub370\uc774\ud130\uc778 \uc8fc\uc2dd \uac00\uaca9 \uc608\uce21\uc5d0 \ud6a8\uacfc\uc801\uc785\ub2c8\ub2e4.<\/p>\n
\uae30\uc874\uc758 RNN\uc740 \uae34 \uc2dc\ud000\uc2a4 \ub370\uc774\ud130\uc5d0\uc11c\uc758 \uc815\ubcf4 \uc190\uc2e4 \ubb38\uc81c(\uc7a5\uae30 \uc758\uc874\uc131 \ubb38\uc81c)\uac00 \uc788\uc2b5\ub2c8\ub2e4. \uc774\ub97c \ud574\uacb0\ud558\uae30 \uc704\ud574 LSTM(Long Short-Term Memory) \ub610\ub294 GRU(Gated Recurrent Unit)\uc640 \uac19\uc740 \ubcc0\ud615\uc774 \ub9ce\uc774 \uc0ac\uc6a9\ub429\ub2c8\ub2e4.<\/p>\n
\uc54c\uace0\ub9ac\uc998 \ud2b8\ub808\uc774\ub529\uc744 \uc704\ud574\uc11c\ub294 \uba3c\uc800 \uc2dc\uacc4\uc5f4 \ub370\uc774\ud130\ub97c \uc218\uc9d1\ud558\uace0 \uc804\ucc98\ub9ac\ud574\uc57c \ud569\ub2c8\ub2e4. \uc77c\ubc18\uc801\uc73c\ub85c \ub2e4\uc74c\uacfc \uac19\uc740 \uc808\ucc28\ub97c \ub530\ub985\ub2c8\ub2e4.<\/p>\n
\ub2e4\uc74c\uc73c\ub85c RNN \ubaa8\ub378\uc744 \uad6c\uc131\ud569\ub2c8\ub2e4. TensorFlow\uc640 Keras\ub97c \uc0ac\uc6a9\ud558\uc5ec \ubaa8\ub378\uc744 \uad6c\ucd95\ud558\ub294 \uac83\uc774 \uc77c\ubc18\uc801\uc785\ub2c8\ub2e4.<\/p>\n
import numpy as np\nimport pandas as pd\nfrom keras.models import Sequential\nfrom keras.layers import Dense, LSTM, Dropout\n\n# \ub370\uc774\ud130 \ubd88\ub7ec\uc624\uae30 \ubc0f \uc804\ucc98\ub9ac \uacfc\uc815\ndata = pd.read_csv('stock_data.csv')\ndata['Normalized'] = (data['Close'] - data['Close'].min()) \/ (data['Close'].max() - data['Close'].min())\n# \ub370\uc774\ud130 \uc2dc\ud000\uc2a4 \uc0dd\uc131\n# X: \uc785\ub825, Y: \ucd9c\ub825\nX, Y = create_dataset(data['Normalized'].values, time_step=10)\n\n# RNN \ubaa8\ub378 \uc0dd\uc131\nmodel = Sequential()\nmodel.add(LSTM(50, return_sequences=True, input_shape=(X.shape[1], 1)))\nmodel.add(Dropout(0.2))\nmodel.add(LSTM(50, return_sequences=False))\nmodel.add(Dropout(0.2))\nmodel.add(Dense(1))\n\nmodel.compile(loss='mean_squared_error', optimizer='adam')<\/code><\/pre>\n4.3 \ubaa8\ub378 \ud6c8\ub828<\/h3>\n
\ubaa8\ub378\uc744 \ud6c8\ub828\uc2dc\ud0a4\uae30 \uc704\ud574 \ud6c8\ub828 \ub370\uc774\ud130\ub97c \uc0ac\uc6a9\ud569\ub2c8\ub2e4.<\/p>\n
model.fit(X_train, Y_train, epochs=100, batch_size=32)<\/code><\/pre>\n4.4 \ubaa8\ub378 \ud3c9\uac00<\/h3>\n
\ubaa8\ub378\uc758 \uc131\ub2a5\uc744 \ud3c9\uac00\ud558\uae30 \uc704\ud574 \ud14c\uc2a4\ud2b8 \ub370\uc774\ud130\ub97c \uc0ac\uc6a9\ud569\ub2c8\ub2e4. \uc77c\ubc18\uc801\uc73c\ub85c RMSE(Root Mean Square Error)\uc640 \uac19\uc740 \uc9c0\ud45c\ub97c \uc0ac\uc6a9\ud558\uc5ec \uc131\ub2a5\uc744 \uce21\uc815\ud569\ub2c8\ub2e4.<\/p>\n
predicted = model.predict(X_test)\nrmse = np.sqrt(np.mean(np.square(predicted - Y_test)))\nprint(\"RMSE:\", rmse)<\/code><\/pre>\n5. \uc804\ub7b5 \uad6c\ud604<\/h2>\n
\ubaa8\ub378\uc774 \ud6c8\ub828\ub41c \ud6c4, \uc2e4\uc81c \uac70\ub798 \uc804\ub7b5\uc744 \uad6c\ud604\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4. \uc5ec\uae30\uc11c \uc608\uce21 \uac00\uaca9\uc774 \ud604\uc7ac \uac00\uaca9\ubcf4\ub2e4 \ub192\uc744 \uacbd\uc6b0 \ub9e4\uc218, \ub0ae\uc744 \uacbd\uc6b0 \ub9e4\ub3c4\ub97c \uacb0\uc815\ud558\ub294 \ub2e8\uc21c\ud55c \uc804\ub7b5\uc744 \uc0ac\uc6a9\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n
for i in range(len(predicted)):\n if predicted[i] > current_price[i]:\n print(\"Buy at:\", current_price[i])\n else:\n print(\"Sell at:\", current_price[i])<\/code><\/pre>\n6. \uacb0\ub860<\/h2>\n
\ubcf8 \uac15\uc88c\uc5d0\uc11c\ub294 \uba38\uc2e0\ub7ec\ub2dd \ubc0f \ub525\ub7ec\ub2dd\uc744 \ud65c\uc6a9\ud55c \uc54c\uace0\ub9ac\uc998 \ud2b8\ub808\uc774\ub529\uc758 \uae30\ucd08\uc640 \uc2ec\uce35 RNN\uc758\u8a2d\uacc4 \ubc29\ubc95\uc744 \uc18c\uac1c\ud558\uc600\uc2b5\ub2c8\ub2e4. \uc2e4\uc81c \uac70\ub798 \uc2dc\uc2a4\ud15c\uc744 \uad6c\ucd95\ud558\uae30 \uc704\ud574\uc11c\ub294 \ub370\uc774\ud130 \uc218\uc9d1, \uc804\ucc98\ub9ac, \ubaa8\ub378 \uc124\uacc4 \ubc0f \uc804\ub7b5 \uad6c\ud604 \ub4f1\uc758 \ub2e4\uc591\ud55c \ub2e8\uacc4\uac00 \ud544\uc694\ud569\ub2c8\ub2e4. \uc2dc\uc7a5\uc758 \ubcc0\ub3d9\uc131\uc5d0 \ub530\ub77c \uc9c0\uc18d\uc801\uc778 \ubaa8\ub378 \uac1c\uc120\uacfc \uc804\ub7b5 \uac80\ud1a0\uac00 \ud544\uc694\ud558\ub2e4\ub294 \uc810\uc744 \uc720\ub150\ud574\uc57c \ud569\ub2c8\ub2e4.<\/p>\n
7. \ucc38\uace0 \ubb38\ud5cc<\/h2>\n