\uc624\ub298\ub0a0 \uae08\uc735\uc2dc\uc7a5\uc5d0\uc11c \uc54c\uace0\ub9ac\uc998 \ud2b8\ub808\uc774\ub529\uc740 \ud544\uc218 \uc694\uc18c\ub85c \uc790\ub9ac \uc7a1\uace0 \uc788\uc2b5\ub2c8\ub2e4. \ud2b9\ud788, \uba38\uc2e0\ub7ec\ub2dd\uacfc \ub525\ub7ec\ub2dd \uae30\ubc95\uc744 \ud65c\uc6a9\ud55c \ud2b8\ub808\uc774\ub529 \uc804\ub7b5\uc740 \ub370\uc774\ud130 \ubd84\uc11d\uc758 \uc815\ud655\ub3c4\ub97c \ub192\uc774\uace0, \ubcf4\ub2e4 \ub098\uc740 \ud22c\uc790 \uacb0\uc815\uc744 \uac00\ub2a5\ud558\uac8c \ud569\ub2c8\ub2e4. \ubcf8 \uac15\uc88c\uc5d0\uc11c\ub294 \uba38\uc2e0\ub7ec\ub2dd \ubc0f \ub525\ub7ec\ub2dd\uc744 \ud1b5\ud55c \uc54c\uace0\ub9ac\uc998 \ud2b8\ub808\uc774\ub529\uc758 \uac1c\uc694\uc640 \ud568\uaed8, \ud30c\uc774\uc36c\uc758 \ud310\ub2e4\uc2a4\ub97c \uc774\uc6a9\ud55c \ub370\uc774\ud130\ub97c \ud6a8\uc728\uc801\uc73c\ub85c \uc800\uc7a5\ud558\uace0 \uad00\ub9ac\ud558\ub294 \ubc29\ubc95\uc5d0 \ub300\ud574 \uc54c\uc544\ubcf4\uaca0\uc2b5\ub2c8\ub2e4.<\/p>\n
\uc54c\uace0\ub9ac\uc998 \ud2b8\ub808\uc774\ub529\uc774\ub780 \uc0ac\uc804\uc5d0 \uc815\uc758\ub41c \uaddc\uce59\uc5d0 \ub530\ub77c \uc790\ub3d9\uc73c\ub85c \ub9e4\ub9e4\ub97c \uc218\ud589\ud558\ub294 \ubc29\ubc95\uc785\ub2c8\ub2e4. \uc5ec\uae30\uc5d0\ub294 \ub2e4\uc591\ud55c \ub370\uc774\ud130 \ubd84\uc11d \uae30\ubc95\uacfc \uc790\ub3d9\ud654 \ud234\uc774 \ud3ec\ud568\ub418\uc5b4 \uc788\uc73c\uba70, \uc8fc\uc2dd, \uc120\ubb3c, \uc635\uc158, \uc678\ud658 \ub4f1 \ub2e4\uc591\ud55c \uc790\uc0b0\uad70\uc5d0\uc11c \ud65c\uc6a9\ub420 \uc218 \uc788\uc2b5\ub2c8\ub2e4. \uc54c\uace0\ub9ac\uc998 \ud2b8\ub808\uc774\ub529\uc758 \uc7a5\uc810\uc740 \uc778\uac04\uc758 \uac10\uc815\uc744 \ubc30\uc81c\ud558\uace0, \uc2e0\uc18d\ud558\uace0 \uc815\ud655\ud558\uac8c \ub9e4\ub9e4\ub97c \uc2e4\ud589\ud560 \uc218 \uc788\ub2e4\ub294 \uc810\uc785\ub2c8\ub2e4.<\/p>\n
\uc54c\uace0\ub9ac\uc998 \ud2b8\ub808\uc774\ub529\uc740 1970\ub144\ub300 \ud6c4\ubc18\ubd80\ud130 \uc2dc\uc791\ub418\uc5c8\uc2b5\ub2c8\ub2e4. \ucd08\uae30\uc5d0\ub294 \ub2e8\uc21c\ud55c \uaddc\uce59 \uae30\ubc18\uc758 \uc2dc\uc2a4\ud15c\uc774\uc5c8\uc9c0\ub9cc, 1990\ub144\ub300 \uc774\ud6c4 \uc778\ud130\ub137\uc758 \ubc1c\uc804\uacfc \ud568\uaed8 \uace0\uc18d \uac70\ub798(HFT, High-Frequency Trading)\uac00 \ub4f1\uc7a5\ud558\uac8c \ub418\uba74\uc11c \ub2e4\uc591\ud55c \uae30\ubc95\uc774 \ubc1c\uc804\ud558\uac8c \ub418\uc5c8\uc2b5\ub2c8\ub2e4.<\/p>\n
\uba38\uc2e0\ub7ec\ub2dd\uc740 \ucef4\ud4e8\ud130\uac00 \uba85\uc2dc\uc801\uc778 \ud504\ub85c\uadf8\ub798\ubc0d \uc5c6\uc774\ub3c4 \uc790\ub3d9\uc73c\ub85c \ud559\uc2b5\ud558\uace0 \uc608\uce21\uc744 \ud560 \uc218 \uc788\ub3c4\ub85d \ud558\ub294 \uae30\uc220\uc785\ub2c8\ub2e4. \ub525\ub7ec\ub2dd\uc740 \uba38\uc2e0\ub7ec\ub2dd\uc758 \ud558\uc704 \ubd84\uc57c\ub85c, \uc778\uacf5 \uc2e0\uacbd\ub9dd\uc744 \uc0ac\uc6a9\ud558\uc5ec \ub370\uc774\ud130\ub97c \ub354 \uae4a\uc774 \uc788\uac8c \ubd84\uc11d\ud569\ub2c8\ub2e4. \uc774 \ub450 \uae30\uc220\uc740 \uae08\uc735\uc2dc\uc7a5\uc5d0\uc11c \ub2e4\uc74c\uacfc \uac19\uc740 \uc6a9\ub3c4\ub85c \uc0ac\uc6a9\ub420 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n
\uba38\uc2e0\ub7ec\ub2dd\uc5d0\uc11c\ub294 \uc8fc\ub85c \ub2e4\uc74c\uacfc \uac19\uc740 \uc54c\uace0\ub9ac\uc998\uc774 \uc0ac\uc6a9\ub429\ub2c8\ub2e4:<\/p>\n
\ub525\ub7ec\ub2dd\uc5d0\uc11c\ub294 \ubcf5\uc7a1\ud55c \ud328\ud134 \uc778\uc2dd\uc744 \uc704\ud574 \ub2e4\uc74c\uacfc \uac19\uc740 \uad6c\uc870\uac00 \ud65c\uc6a9\ub429\ub2c8\ub2e4:<\/p>\n
\uc54c\uace0\ub9ac\uc998 \ud2b8\ub808\uc774\ub529\uc5d0\uc11c \ub370\uc774\ud130\ub294 \ud575\uc2ec\uc785\ub2c8\ub2e4. \ub370\uc774\ud130\ub97c \uc218\uc9d1\ud558\uace0 \ud6a8\uc728\uc801\uc73c\ub85c \uc800\uc7a5\ud558\ub294 \uac83\uc740 \ubaa8\ub378\uc758 \uc131\ub2a5\uc5d0 \ud070 \uc601\ud5a5\uc744 \ubbf8\uce58\uae30 \ub54c\ubb38\uc785\ub2c8\ub2e4.<\/p>\n
\uae08\uc735 \ub370\uc774\ud130\ub97c \uc218\uc9d1\ud558\ub294 \ubc29\ubc95\uc740 \ub2e4\uc591\ud569\ub2c8\ub2e4. \uc608\ub97c \ub4e4\uc5b4, API\ub97c \ud1b5\ud574 \uc2e4\uc2dc\uac04 \ub370\uc774\ud130\ub97c \uc218\uc9d1\ud558\uac70\ub098, \uc6f9 \uc2a4\ud06c\ub798\ud551\uc744 \ud1b5\ud574 \uacfc\uac70 \ub370\uc774\ud130\ub97c \ubaa8\uc744 \uc218 \uc788\uc2b5\ub2c8\ub2e4. \ub370\uc774\ud130 \uc81c\uacf5 \uc5c5\uccb4\uc5d0\uc11c \uad6c\uc785\ud558\ub294 \uac83\ub3c4 \ud55c \uac00\uc9c0 \ubc29\ubc95\uc785\ub2c8\ub2e4.<\/p>\n
\ud310\ub2e4\uc2a4(Pandas)\ub294 \ud30c\uc774\uc36c\uc5d0\uc11c \ub370\uc774\ud130 \ubd84\uc11d\uc744 \uc704\ud55c \uac15\ub825\ud55c \ub77c\uc774\ube0c\ub7ec\ub9ac\uc785\ub2c8\ub2e4. \ub370\uc774\ud130\ud504\ub808\uc784(DataFrame) \uac1d\uccb4\ub97c \uc0ac\uc6a9\ud558\uc5ec \uc190\uc27d\uac8c \ub370\uc774\ud130\ub97c \uc870\uc791\ud558\uace0 \ubd84\uc11d\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n
# \uc608\uc2dc \ucf54\ub4dc\nimport pandas as pd\n\ndata = {\n '\ub0a0\uc9dc': ['2021-01-01', '2021-01-02', '2021-01-03'],\n '\uc885\uac00': [100, 101, 102]\n}\n\ndf = pd.DataFrame(data)\ndf.to_csv('stock_data.csv', index=False)\n<\/code><\/pre>\n3.2.2 \ub370\uc774\ud130\ubca0\uc774\uc2a4\ub97c \ud1b5\ud55c \ub370\uc774\ud130 \uc800\uc7a5<\/h4>\n
\ud310\ub2e4\uc2a4\ub294 SQL \ub370\uc774\ud130\ubca0\uc774\uc2a4\uc640\ub3c4 \uc27d\uac8c \uc5f0\uacb0\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4. \uc544\ub798\ub294 SQLite\ub97c \uc774\uc6a9\ud55c \uc608\uc2dc\uc785\ub2c8\ub2e4.<\/p>\n
# \uc608\uc2dc \ucf54\ub4dc\nimport sqlite3\n\n# SQLite \ub370\uc774\ud130\ubca0\uc774\uc2a4 \uc5f0\uacb0\nconn = sqlite3.connect('stock_data.db')\n\n# \ud310\ub2e4\uc2a4 \ub370\uc774\ud130\ud504\ub808\uc784\uc744 SQL \ud14c\uc774\ube14\ub85c \uc800\uc7a5\ndf.to_sql('stock_prices', conn, if_exists='replace', index=False)\n<\/code><\/pre>\n4. \uba38\uc2e0\ub7ec\ub2dd \ubaa8\ub378 \uad6c\ucd95<\/h2>\n
\ubd84\uc11d\uc5d0 \uc0ac\uc6a9\ud560 \ub370\uc774\ud130\ub97c \uc900\ube44\ud55c \ud6c4, \uc774\uc81c \uba38\uc2e0\ub7ec\ub2dd \ubaa8\ub378\uc744 \uad6c\ucd95\ud560 \ucc28\ub840\uc785\ub2c8\ub2e4. \uc774\ub97c \ud1b5\ud574 \ud5a5\ud6c4 \uc8fc\uac00\uc758 \ubc29\ud5a5\uc131\uc744 \uc608\uce21\ud574 \ubcfc \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n
4.1 \ub370\uc774\ud130 \uc804\ucc98\ub9ac<\/h3>\n
\ubaa8\ub378\uc5d0 \ub370\uc774\ud130\ub97c \uc785\ub825\ud558\uae30 \uc804\uc5d0 \uc804\ucc98\ub9ac \uacfc\uc815\uc774 \ud544\uc694\ud569\ub2c8\ub2e4. \uacb0\uce21\uce58 \ucc98\ub9ac, \ub370\uc774\ud130 \uc815\uaddc\ud654 \ubc0f \ud2b9\uc131 \uc120\ud0dd\uc774 \ud3ec\ud568\ub429\ub2c8\ub2e4.<\/p>\n
4.1.1 \uacb0\uce21\uce58 \ucc98\ub9ac<\/h4>\n# \uc608\uc2dc \ucf54\ub4dc\ndf.fillna(method='ffill', inplace=True) # \uc55e\uc758 \uac12\uc73c\ub85c \uacb0\uce21\uce58 \ucc44\uc6b0\uae30\n<\/code><\/pre>\n4.1.2 \ub370\uc774\ud130 \uc815\uaddc\ud654<\/h4>\n# \uc608\uc2dc \ucf54\ub4dc\nfrom sklearn.preprocessing import MinMaxScaler\n\nscaler = MinMaxScaler()\ndf['\uc815\uaddc\ud654\ub41c \uc885\uac00'] = scaler.fit_transform(df[['\uc885\uac00']])\n<\/code><\/pre>\n4.2 \uba38\uc2e0\ub7ec\ub2dd \ubaa8\ub378 \ud559\uc2b5<\/h3>\n
\ub370\uc774\ud130\uac00 \uc900\ube44\ub418\uc5c8\uc73c\uba74, \uc774\uc81c \ubaa8\ub378\uc744 \ud559\uc2b5\uc2dc\ud0ac \uc218 \uc788\uc2b5\ub2c8\ub2e4. \uc544\ub798\ub294 \ub79c\ub364 \ud3ec\ub808\uc2a4\ud2b8 \uc54c\uace0\ub9ac\uc998\uc744 \uc774\uc6a9\ud55c \uc608\uc2dc\uc785\ub2c8\ub2e4.<\/p>\n
# \uc608\uc2dc \ucf54\ub4dc\nfrom sklearn.ensemble import RandomForestRegressor\nfrom sklearn.model_selection import train_test_split\n\nX = df[['\ud2b9\uc1311', '\ud2b9\uc1312']] # \uc0ac\uc6a9\ud560 \ud2b9\uc131\ny = df['\uc885\uac00'] # \ubaa9\ud45c \ubcc0\uc218\n\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n\nmodel = RandomForestRegressor()\nmodel.fit(X_train, y_train)\n<\/code><\/pre>\n5. \ub525\ub7ec\ub2dd \ubaa8\ub378 \uad6c\ucd95<\/h2>\n
\ub525\ub7ec\ub2dd \ubaa8\ub378\uc740 \ubcf4\ub2e4 \ubcf5\uc7a1\ud55c \ud328\ud134\uc744 \uc778\uc2dd\ud560 \uc218 \uc788\ub294 \uac15\ub825\ud55c \ub3c4\uad6c\uc785\ub2c8\ub2e4. Keras \ub77c\uc774\ube0c\ub7ec\ub9ac\ub97c \uc0ac\uc6a9\ud558\uc5ec \uac04\ub2e8\ud55c \uc2e0\uacbd\ub9dd \uad6c\uc870\ub97c \ub9cc\ub4e4 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n
5.1 Keras \ubaa8\ub378 \uad6c\uc131<\/h3>\n# \uc608\uc2dc \ucf54\ub4dc\nfrom keras.models import Sequential\nfrom keras.layers import Dense\n\nmodel = Sequential()\nmodel.add(Dense(64, activation='relu', input_shape=(X_train.shape[1],)))\nmodel.add(Dense(32, activation='relu'))\nmodel.add(Dense(1)) # \ucd9c\ub825\uce35\n\nmodel.compile(optimizer='adam', loss='mean_squared_error')\nmodel.fit(X_train, y_train, epochs=50, batch_size=10)\n<\/code><\/pre>\n6. \uacb0\uacfc \ud3c9\uac00 \ubc0f \uc2dc\uac01\ud654<\/h2>\n
\ubaa8\ub378\uc774 \ud559\uc2b5\ub41c \ud6c4, \uc131\ub2a5 \ud3c9\uac00\uc640 \uc2dc\uac01\ud654\ub97c \ud1b5\ud574 \uc608\uce21 \uacb0\uacfc\ub97c \ubd84\uc11d\ud569\ub2c8\ub2e4.<\/p>\n
6.1 \uc131\ub2a5 \ud3c9\uac00<\/h3>\n# \uc608\uc2dc \ucf54\ub4dc\nfrom sklearn.metrics import mean_squared_error\n\ny_pred = model.predict(X_test)\nmse = mean_squared_error(y_test, y_pred)\nprint(f'Mean Squared Error: {mse}')\n<\/code><\/pre>\n6.2 \uc2dc\uac01\ud654<\/h3>\n
Matplotlib\uc744 \uc774\uc6a9\ud558\uc5ec \uc608\uce21 \uacb0\uacfc\ub97c \uc2dc\uac01\ud654\ud569\ub2c8\ub2e4.<\/p>\n
# \uc608\uc2dc \ucf54\ub4dc\nimport matplotlib.pyplot as plt\n\nplt.plot(y_test.values, label='Actual')\nplt.plot(y_pred, label='Predicted')\nplt.legend()\nplt.show()\n<\/code><\/pre>\n7. \uacb0\ub860 \ubc0f \ud5a5\ud6c4 \uacfc\uc81c<\/h2>\n
\ubcf8 \uac15\uc88c\ub97c \ud1b5\ud574 \uba38\uc2e0\ub7ec\ub2dd \ubc0f \ub525\ub7ec\ub2dd\uc744 \ud65c\uc6a9\ud55c \uc54c\uace0\ub9ac\uc998 \ud2b8\ub808\uc774\ub529\uc758 \uae30\ubcf8 \uac1c\ub150\uacfc \ub370\uc774\ud130 \uc800\uc7a5 \ubc29\ubc95\uc744 \ubc30\uc6e0\uc2b5\ub2c8\ub2e4. \ud5a5\ud6c4 \ub354 \ub098\uc544\uac00 \uc774\ub97c \ub2e4\ub978 \uc790\uc0b0\uad70\uc5d0 \ud655\uc7a5\ud558\uac70\ub098, \uc559\uc0c1\ube14 \uae30\ubc95\uc744 \uc801\uc6a9\ud558\uc5ec \ubaa8\ud615\uc744 \uac1c\uc120\ud558\ub294 \ub4f1\uc758 \uc5f0\uad6c\uac00 \ud544\uc694\ud560 \uac83\uc785\ub2c8\ub2e4.<\/p>\n
\ucc38\uace0 \ubb38\ud5cc<\/h2>\n