\n \uae08\uc735 \uc2dc\uc7a5\uc5d0\uc11c\uc758 \ud2b8\ub808\uc774\ub529 \uc54c\uace0\ub9ac\uc998\uc740 \ub9e4\uc77c \uc5c4\uccad\ub09c \uc591\uc758 \ub370\uc774\ud130\ub97c \ubd84\uc11d\ud558\uace0, \uc774\ub97c \ubc14\ud0d5\uc73c\ub85c buy \ub610\ub294 sell \uacb0\uc815\uc744 \ub0b4\ub9bd\ub2c8\ub2e4. \uc774\ub7ec\ud55c \uc790\ub3d9\ud654\ub41c \uc2dc\uc2a4\ud15c\uc758 \ud575\uc2ec\uc5d0\ub294 \uba38\uc2e0\ub7ec\ub2dd \ubc0f \ub525\ub7ec\ub2dd \uc54c\uace0\ub9ac\uc998\uc774 \uc788\uc2b5\ub2c8\ub2e4. \ubcf8 \uac15\uc88c\uc5d0\uc11c\ub294 \uba38\uc2e0\ub7ec\ub2dd \uc54c\uace0\ub9ac\uc998 \uc911\uc5d0\uc11c\ub3c4 \uc120\ud615 \ubd84\ub958\ub97c \uc0ac\uc6a9\ud558\uc5ec \ud000\ud2b8 \ub9e4\ub9e4\ub97c \uad6c\ud604\ud558\ub294 \ubc29\ubc95\uc5d0 \ub300\ud574 \uc790\uc138\ud788 \uc124\uba85\ud558\uaca0\uc2b5\ub2c8\ub2e4.\n <\/p>\n
\n \uc54c\uace0\ub9ac\uc998 \ud2b8\ub808\uc774\ub529\uc774\ub780 \ud2b9\uc815 \uaddc\uce59 \uae30\ubc18\uc758 \ud504\ub85c\uadf8\ub7a8\uc774 \uae08\uc735\uc2dc\uc7a5\uc5d0 \ub300\ud574 \uc790\ub3d9\uc73c\ub85c \uac70\ub798\ub97c \uc218\ud589\ud558\ub294 \ubc29\uc2dd\uc785\ub2c8\ub2e4. \uc77c\ubc18\uc801\uc73c\ub85c \uc18d\ub3c4\uc640 \ud6a8\uc728\uc131\uc744 \uc99d\uac00\uc2dc\ud0a4\uae30 \uc704\ud574 \uace0\ube48\ub3c4 \ud2b8\ub808\uc774\ub529(High-Frequency Trading, HFT) \uac19\uc740 \uae30\ubc95\uc774 \uc0ac\uc6a9\ub429\ub2c8\ub2e4. \uc774\ub7ec\ud55c \uc54c\uace0\ub9ac\uc998\uc740 \ub2e4\uc591\ud55c \ub370\uc774\ud130\ub97c \uc2e4\uc2dc\uac04\uc73c\ub85c \ubd84\uc11d\ud558\uace0, \uc5ec\ub7ec \uac00\uc9c0 \uac70\ub798 \uc804\ub7b5\uc744 \uc801\uc6a9\ud558\uc5ec \ucd5c\uc801\uc758 \uc2dc\uc810\uc5d0 \ub9e4\ub9e4 \uacb0\uc815\uc744 \ub0b4\ub9b4 \uc218 \uc788\uc2b5\ub2c8\ub2e4.\n <\/p>\n
\n \uba38\uc2e0\ub7ec\ub2dd\uc740 \uacfc\uac70\uc758 \ub370\uc774\ud130\ub97c \ubc14\ud0d5\uc73c\ub85c \ud328\ud134\uc744 \ud559\uc2b5\ud558\uace0, \uc774\ub97c \ubbf8\ub798\uc758 \ub370\uc774\ud130 \uc608\uce21\uc5d0 \ud65c\uc6a9\ud558\ub294 \uae30\ubc95\uc785\ub2c8\ub2e4. \uc54c\uace0\ub9ac\uc998 \ud2b8\ub808\uc774\ub529\uc5d0 \uc788\uc5b4\uc11c \uba38\uc2e0\ub7ec\ub2dd\uc758 \uc774\uc810\uc740 \ub2e4\uc74c\uacfc \uac19\uc2b5\ub2c8\ub2e4:\n <\/p>\n
\n \uc120\ud615 \ubd84\ub958\ub294 \ub370\uc774\ud130\ub97c \uc120\ud615 \uacbd\uacc4\ub85c \uad6c\ubd84\ud558\ub294 \uae30\ubcf8\uc801\uc778 \uba38\uc2e0\ub7ec\ub2dd \uae30\ubc95\uc785\ub2c8\ub2e4. \ub300\ud45c\uc801\uc778 \uc54c\uace0\ub9ac\uc998\uc73c\ub85c\ub294 \ub85c\uc9c0\uc2a4\ud2f1 \ud68c\uadc0(Logistic Regression)\uc640 \uc11c\ud3ec\ud2b8 \ubca1\ud130 \uba38\uc2e0(Support Vector Machine, SVM)\uc774 \uc788\uc2b5\ub2c8\ub2e4. \uc120\ud615 \ubd84\ub958\ub294 \ub2e4\uc74c\uacfc \uac19\uc740 \uc8fc\uc694 \uc694\uc18c\ub85c \uad6c\uc131\ub429\ub2c8\ub2e4:\n <\/p>\n
\n \uc54c\uace0\ub9ac\uc998 \ud2b8\ub808\uc774\ub529\uc5d0\uc11c \ub370\uc774\ud130\ub294 \uc0dd\uba85\uacfc\ub3c4 \uac19\uc2b5\ub2c8\ub2e4. \uc8fc\uac00 \ub370\uc774\ud130, \uac70\ub798\ub7c9, \uacbd\uc81c \uc9c0\ud45c \ub4f1 \ub2e4\uc591\ud55c \ub370\uc774\ud130\ub97c \uc218\uc9d1\ud574\uc57c \ud569\ub2c8\ub2e4. \ub370\uc774\ud130\ub97c \uc218\uc9d1\ud55c \ud6c4\uc5d0\ub294 \uc5ec\ub7ec \uc804\ucc98\ub9ac \uacfc\uc815\uc744 \uac70\uce58\ub294 \uac83\uc774 \ud544\uc218\uc801\uc785\ub2c8\ub2e4. \uc804\ucc98\ub9ac \uacfc\uc815\uc740 \ub2e4\uc74c\uacfc \uac19\uc2b5\ub2c8\ub2e4:\n <\/p>\n
\nimport pandas as pd\nimport yfinance as yf\n\n# \uc8fc\uc2dd \ub370\uc774\ud130 \uc218\uc9d1\ndata = yf.download(\"AAPL\", start=\"2020-01-01\", end=\"2023-01-01\")\ndata.to_csv(\"AAPL.csv\")\n <\/pre>\n4.2 \ub370\uc774\ud130 \uc804\ucc98\ub9ac \uc608\uc81c<\/h3>\n
\n# \uacb0\uce21\uce58 \ucc98\ub9ac\ndata.fillna(method='ffill', inplace=True)\n\n# \ud53c\ucc98 \uc0dd\uc131 \uc608\uc2dc: 50\uc77c \uc774\ub3d9 \ud3c9\uade0 \ucd94\uac00\ndata['MA50'] = data['Close'].rolling(window=50).mean()\n <\/pre>\n5. \uc120\ud615 \ubd84\ub958 \ubaa8\ub378 \ud559\uc2b5<\/h2>\n
\n \ub370\uc774\ud130 \uc900\ube44\uac00 \uc644\ub8cc\ub418\uba74, \uba38\uc2e0\ub7ec\ub2dd \ubaa8\ub378\uc744 \ud559\uc2b5\uc2dc\ud0ac \uc218 \uc788\uc2b5\ub2c8\ub2e4. \uc774\ubc88 \uac15\uc88c\uc5d0\uc11c\ub294 \ub85c\uc9c0\uc2a4\ud2f1 \ud68c\uadc0\ub97c \uc0ac\uc6a9\ud558\uc5ec \ub9e4\ub9e4 \uc2e0\ud638\ub97c \uc608\uce21\ud574 \ubcf4\uaca0\uc2b5\ub2c8\ub2e4. \ub85c\uc9c0\uc2a4\ud2f1 \ud68c\uadc0\ub294 \uc120\ud615 \ubd84\ub958\uc758 \uae30\ucd08\ub85c\uc11c \ub2e4\uc74c\uacfc \uac19\uc774 \uc9c4\ud589\ub429\ub2c8\ub2e4.\n <\/p>\n
5.1 \ub370\uc774\ud130 \uc900\ube44<\/h3>\n
\nfrom sklearn.model_selection import train_test_split\n\n# \uc785\ub825 \ud53c\ucc98\uc640 \ud0c0\uac9f \ub808\uc774\ube14 \uc815\uc758\nX = data[['Close', 'MA50']]\ny = (data['Close'].shift(-1) > data['Close']).astype(int) # \ub2e4\uc74c \ub0a0 \uc8fc\uac00\uac00 \uc624\ub97c \uac83\uc778\uc9c0 \uc5ec\ubd80\n\n# \ud559\uc2b5 \ub370\uc774\ud130\uc640 \ud14c\uc2a4\ud2b8 \ub370\uc774\ud130\ub85c \ubd84\ud560\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n <\/pre>\n5.2 \ubaa8\ub378 \ud559\uc2b5<\/h3>\n
\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.metrics import accuracy_score\n\n# \ub85c\uc9c0\uc2a4\ud2f1 \ud68c\uadc0 \ubaa8\ub378 \uc0dd\uc131\nmodel = LogisticRegression()\nmodel.fit(X_train, y_train) # \ubaa8\ub378 \ud559\uc2b5\n\n# \ud14c\uc2a4\ud2b8 \ub370\uc774\ud130 \uc608\uce21\ny_pred = model.predict(X_test)\n\n# \uc815\ud655\ub3c4 \ud655\uc778\naccuracy = accuracy_score(y_test, y_pred)\nprint(f\"\uc815\ud655\ub3c4: {accuracy:.2f}\")\n <\/pre>\n6. \uacb0\uacfc \ud3c9\uac00<\/h2>\n
\n \ubaa8\ub378\uc758 \uc131\ub2a5\uc744 \ud3c9\uac00\ud558\uae30 \uc704\ud574 \ub2e4\uc591\ud55c \uc9c0\ud45c\ub97c \uc0ac\uc6a9\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4. \uc774 \uac15\uc88c\uc5d0\uc11c\ub294 \uc815\ud655\ub3c4 \uc678\uc5d0\ub3c4 \ud63c\ub3d9 \ud589\ub82c(Confusion Matrix)\uacfc ROC \uace1\uc120(Receiver Operating Characteristic Curve)\uc5d0 \ub300\ud574 \uc124\uba85\ud558\uaca0\uc2b5\ub2c8\ub2e4.\n <\/p>\n
6.1 \ud63c\ub3d9 \ud589\ub82c<\/h3>\n
\nfrom sklearn.metrics import confusion_matrix\nimport seaborn as sns\nimport matplotlib.pyplot as plt\n\n# \ud63c\ub3d9 \ud589\ub82c \uc0dd\uc131\ncm = confusion_matrix(y_test, y_pred)\n\n# \uc2dc\uac01\ud654\nsns.heatmap(cm, annot=True, fmt='d', cmap='Blues')\nplt.title(\"\ud63c\ub3d9 \ud589\ub82c\")\nplt.xlabel(\"\uc608\uce21 \uac12\")\nplt.ylabel(\"\uc2e4\uc81c \uac12\")\nplt.show()\n <\/pre>\n6.2 ROC \uace1\uc120<\/h3>\n
\nfrom sklearn.metrics import roc_curve, auc\n\n# ROC \uace1\uc120 \ub370\uc774\ud130 \uacc4\uc0b0\nfpr, tpr, _ = roc_curve(y_test, model.predict_proba(X_test)[:,1])\nroc_auc = auc(fpr, tpr)\n\n# ROC \uace1\uc120 \uc2dc\uac01\ud654\nplt.plot(fpr, tpr, color='darkorange', lw=2, label='ROC \uace1\uc120 (area = %0.2f)' % roc_auc)\nplt.plot([0, 1], [0, 1], color='navy', lw=2, linestyle='--')\nplt.xlim([0.0, 1.0])\nplt.ylim([0.0, 1.05])\nplt.xlabel('\uac70\uc9d3 \uc591\uc131 \ube44\uc728')\nplt.ylabel('\uc9c4\uc9dc \uc591\uc131 \ube44\uc728')\nplt.title('\uc218\uc2e0\uc790 \uc870\uc791 \ud2b9\uc131 \uace1\uc120')\nplt.legend(loc=\"lower right\")\nplt.show()\n <\/pre>\n7. \uc2e4\uc804 \uc801\uc6a9 \ubc0f \uacb0\ub860<\/h2>\n
\n \uc120\ud615 \ubd84\ub958 \ubaa8\ub378\uc744 \uc774\uc6a9\ud55c \uc54c\uace0\ub9ac\uc998 \ud2b8\ub808\uc774\ub529\uc740 \uc2dc\uc7a5\uc5d0\uc11c\uc758 \ub9e4\ub9e4 \uc2e0\ud638\ub97c \uc790\ub3d9\uc73c\ub85c \uc0dd\uc131\ud558\ub294 \ub370 \uc720\uc6a9\ud569\ub2c8\ub2e4. \uadf8\ub7ec\ub098 \uc774 \ubc29\ubc95\uc740 \ud55c\uacc4\uac00 \uc788\uc73c\uba70, \ubcf5\uc7a1\ud55c \uc2dc\uc7a5\uc5d0\uc11c\ub294 \ube44\uc120\ud615 \ubaa8\ub378\uc774\ub098 \ub354 \ubc1c\uc804\ub41c \ub525\ub7ec\ub2dd \uae30\ubc95\uc744 \uc0ac\uc6a9\ud560 \ud544\uc694\uac00 \uc788\uc2b5\ub2c8\ub2e4. \uae30\uacc4\ud559\uc2b5 \uc54c\uace0\ub9ac\uc998\uc744 \uc0ac\uc6a9\ud55c \ud2b8\ub808\uc774\ub529 \uc2dc\uc2a4\ud15c\uc740 \uc9c0\uc18d\uc801\uc778 \ud559\uc2b5\uacfc \uac1c\uc120\uc774 \ud544\uc694\ud558\uba70, \uc801\uc808\ud55c \ubc31\ud14c\uc2a4\ud305\uacfc \ub9ac\uc2a4\ud06c \uad00\ub9ac\ub3c4 \ud544\uc218\uc801\uc785\ub2c8\ub2e4.\n <\/p>\n
\n \uc774 \uac15\uc88c\uc5d0\uc11c\ub294 \uba38\uc2e0\ub7ec\ub2dd\uacfc \uc120\ud615 \ubd84\ub958\ub97c \ud1b5\ud55c \ud2b8\ub808\uc774\ub529 \uc2dc\uc2a4\ud15c\uc758 \uae30\ubcf8\uc801\uc778 \uac1c\ub150\uacfc \uad6c\ud604 \ubc29\ubc95\uc744 \ub2e4\ub8e8\uc5c8\uc2b5\ub2c8\ub2e4. \ub354\uc6b1 \ubc1c\uc804\ub41c \uc54c\uace0\ub9ac\uc998\uc774\ub098 \ub525\ub7ec\ub2dd \uae30\ubc95\uc5d0 \ub300\ud574\uc11c\ub3c4 \uc9c0\uc18d\uc801\uc73c\ub85c \ud559\uc2b5\ud558\ub294 \uac83\uc774 \uc911\uc694\ud569\ub2c8\ub2e4. \uac10\uc0ac\ud569\ub2c8\ub2e4!\n <\/p>\n
<\/body><\/p>\n","protected":false},"excerpt":{"rendered":"