{"id":2336,"date":"2025-06-02T07:40:00","date_gmt":"2025-06-01T23:40:00","guid":{"rendered":"https:\/\/blog.laoyulaoyu.top\/?p=2336"},"modified":"2025-05-27T12:40:27","modified_gmt":"2025-05-27T04:40:27","slug":"ai%e4%b8%8e%e9%87%8f%e5%8c%96%ef%bc%9a%e8%a7%a3%e6%9e%84%e8%b6%8b%e5%8a%bf%e5%8a%a0%e9%80%9f%e5%ba%a6%e7%ad%96%e7%95%a5%ef%bc%8c%e8%ae%a9%e4%bd%a0%e9%a2%86%e5%85%88%e4%b8%80%e6%ad%a5","status":"publish","type":"post","link":"https:\/\/www.laoyulaoyu.com\/index.php\/2025\/06\/02\/ai%e4%b8%8e%e9%87%8f%e5%8c%96%ef%bc%9a%e8%a7%a3%e6%9e%84%e8%b6%8b%e5%8a%bf%e5%8a%a0%e9%80%9f%e5%ba%a6%e7%ad%96%e7%95%a5%ef%bc%8c%e8%ae%a9%e4%bd%a0%e9%a2%86%e5%85%88%e4%b8%80%e6%ad%a5\/","title":{"rendered":"AI\u4e0e\u91cf\u5316\uff1a\u89e3\u6784\u201c\u8d8b\u52bf\u52a0\u901f\u5ea6\u201d\u7b56\u7565\uff0c\u8ba9\u4f60\u9886\u5148\u4e00\u6b65\u628a\u63e1\u884c\u60c5"},"content":{"rendered":"\n

\u4f5c \u8005\uff1a\u8001\u4f59\u635e\u9c7c<\/a><\/p>\n\n\n\n

\u539f\u521b\u4e0d\u6613\uff0c\u8f6c\u8f7d\u8bf7\u6807\u660e\u51fa\u5904\u53ca\u539f\u4f5c\u8005\u3002<\/mark><\/strong><\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n
\n
\u5199\u5728\u524d\u9762\u7684\u8bdd\uff1a<\/strong>\u6211\u53d1\u73b0\u4e86\u4e00\u4e2a\u85cf\u5728\u80a1\u4ef7\u6ce2\u52a8\u4e2d\u7684\u6570\u5b66\u89c4\u5f8b\uff1a\u80a1\u7968\u8d8b\u52bf\u7684\u52a0\u901f\u5ea6\u6bd4\u4ef7\u683c\u672c\u8eab\u66f4\u80fd\u9884\u6d4b\u6da8\u8dcc\uff01\u901a\u8fc7\u8ba1\u7b97\u80a1\u4ef7\u8d8b\u52bf\u7684\u201c\u52a0\u901f\u5ea6\u201d\uff0c\u63d0\u524d\u8bc6\u522b\u5e02\u573a\u7684\u8f6c\u6298\u70b9\u3002<\/strong><\/mark>\u5229\u7528\u8fd9\u4e2a\u7b56\u7565\uff0c\u6211\u4eec\u53ef\u4ee5\u5728\u522b\u4eba\u8fd8\u6ca1\u53cd\u5e94\u8fc7\u6765\u65f6\uff0c\u5148\u4e00\u6b65\u505a\u51fa\u51b3\u7b56\u3002\u8fd9\u4e0d\u4ec5\u63d0\u9ad8\u4e86\u60a8\u7684\u4ea4\u6613\u6210\u529f\u7387\uff0c\u4e5f\u8ba9\u5927\u5bb6\u5728\u5e02\u573a\u4e2d\u66f4\u52a0\u4ece\u5bb9\u3002<\/pre>\n<\/blockquote>\n\n\n\n
\u4e00\u3001\u4ec0\u4e48\u662f\u8d8b\u52bf\u52a0\u901f\u5ea6<\/strong><\/h2>\n\n\n\n
\u5728\u80a1\u5e02\u4e2d\uff0c\u5f88\u591a\u4eba\u603b\u662f\u7b49\u5230\u8d8b\u52bf\u660e\u663e\u540e\u624d\u8ddf\u8fdb\uff0c\u7ed3\u679c\u5f80\u5f80\u9519\u8fc7\u4e86\u6700\u4f73\u65f6\u673a\u3002\u6709\u6ca1\u6709\u529e\u6cd5\u63d0\u524d\u53d1\u73b0\u8d8b\u52bf\u7684\u8f6c\u6298\u70b9\u5462\uff1f\u4eca\u5929\uff0c\u6211\u8981\u5206\u4eab\u4e00\u4e2a\u57fa\u4e8e\u7269\u7406\u5b66\u6982\u5ff5\u7684\u4ea4\u6613\u7b56\u7565\u2014\u2014\u8d8b\u52bf\u52a0\u901f\u5ea6\uff08Trend Acceleration\uff09\uff0c\u5e2e\u52a9\u4f60\u9886\u5148\u4e00\u6b65\u628a\u63e1\u5e02\u573a\u673a\u4f1a\u3002<\/p>\n\n\n\n
1.1 \u4ece\u7269\u7406\u5b66\u770b\u5e02\u573a<\/strong><\/h3>\n\n\n\n
\u6211\u4eec\u53ef\u4ee5\u628a\u80a1\u4ef7\u7684\u53d8\u5316\u7c7b\u6bd4\u4e3a\u7269\u4f53\u7684\u8fd0\u52a8\uff1a<\/p>\n\n\n\n
\"\"<\/figure>\n\n\n\n
    \n
  • \u4f4d\u7f6e\uff08Position\uff09<\/strong>\uff1a\u5f53\u524d\u7684\u80a1\u4ef7\u3002<\/li>\n\n\n\n
  • \u901f\u5ea6\uff08Velocity\uff09<\/strong>\uff1a\u80a1\u4ef7\u7684\u53d8\u5316\u901f\u5ea6\uff0c\u5373\u8d8b\u52bf\u7684\u659c\u7387\u3002<\/li>\n\n\n\n
  • \u52a0\u901f\u5ea6\uff08Acceleration\uff09<\/strong>\uff1a\u8d8b\u52bf\u53d8\u5316\u7684\u901f\u5ea6\uff0c\u5373\u8d8b\u52bf\u659c\u7387\u7684\u53d8\u5316\u7387\u3002<\/li>\n<\/ul>\n\n\n\n
    \u901a\u8fc7\u5206\u6790\u8d8b\u52bf\u7684\u52a0\u901f\u5ea6\uff0c\u6211\u4eec\u53ef\u4ee5\u63d0\u524d\u53d1\u73b0\u8d8b\u52bf\u7684\u51cf\u5f31\u6216\u589e\u5f3a\uff0c\u4ece\u800c\u9884\u6d4b\u5e02\u573a\u7684\u8f6c\u6298\u70b9\u3002<\/p>\n\n\n\n
    1.2 \u7b56\u7565\u539f\u7406<\/strong><\/h3>\n\n\n\n
    \u8fd9\u4e2a\u7b56\u7565\u7684\u6838\u5fc3\u662f\u8ba1\u7b97\u80a1\u4ef7\u79fb\u52a8\u5e73\u5747\u7ebf\u7684\u659c\u7387\uff0c\u7136\u540e\u518d\u8ba1\u7b97\u8fd9\u4e2a\u659c\u7387\u7684\u53d8\u5316\u7387\uff0c\u5373\u52a0\u901f\u5ea6\u3002<\/p>\n\n\n\n
    \"\"<\/figure>\n\n\n\n
      \n
    • \u4e70\u5165\u4fe1\u53f7<\/strong>\uff1a\u5f53\u52a0\u901f\u5ea6\u4ece\u8d1f\u8f6c\u6b63\uff0c\u4e14\u8d8b\u52bf\u659c\u7387\u4ecd\u4e3a\u8d1f\u65f6\uff0c\u8bf4\u660e\u4e0b\u8dcc\u8d8b\u52bf\u51cf\u5f31\uff0c\u53ef\u80fd\u5373\u5c06\u53cd\u8f6c\u4e3a\u4e0a\u6da8\u8d8b\u52bf\u3002<\/li>\n\n\n\n
    • \u5356\u51fa\u4fe1\u53f7<\/strong>\uff1a\u5f53\u52a0\u901f\u5ea6\u4ece\u6b63\u8f6c\u8d1f\uff0c\u4e14\u8d8b\u52bf\u659c\u7387\u4ecd\u4e3a\u6b63\u65f6\uff0c\u8bf4\u660e\u4e0a\u6da8\u8d8b\u52bf\u51cf\u5f31\uff0c\u53ef\u80fd\u5373\u5c06\u53cd\u8f6c\u4e3a\u4e0b\u8dcc\u8d8b\u52bf\u3002<\/li>\n<\/ul>\n\n\n\n
      \u8fd9\u4e2a\u7b56\u7565\u7684\u4f18\u52bf\u5728\u4e8e\u63d0\u524d\u53d1\u73b0\u8d8b\u52bf\u7684\u53d8\u5316\uff0c\u907f\u514d\u5728\u8d8b\u52bf\u660e\u663e\u540e\u624d\u8ddf\u8fdb\uff0c\u4ece\u800c\u63d0\u9ad8\u4ea4\u6613\u7684\u6210\u529f\u7387\u3002<\/p>\n\n\n\n
      \u4e8c\u3001\u5b9e\u6218\u6848\u4f8b\u5206\u4eab<\/strong><\/h2>\n\n\n\n
      \u8ba9\u6211\u4eec\u770b\u770b\u8d8b\u52bf\u52a0\u901f\u5ea6\u7b56\u7565\u57282025\u5e741\u67081\u65e5\u81f35\u670821\u65e5\u7684\u7279\u65af\u62c9\uff08TSLA\uff09\u5b9e\u6218\u4e2d\u7684\u8868\u73b0\u3002\u4ee5\u4e0b\u662f\u5173\u952e\u56de\u6d4b\u6570\u636e\uff1a<\/p>\n\n\n\n
      \u4e70\u5165\u6301\u6709\u6536\u76ca\u7387: -10.08%
      \u7b56\u7565\u6536\u76ca\u7387: 25.35%

      \u6570\u636e\u8d28\u91cf\u68c0\u67e5:
      \u7f3a\u5931\u503c:  102
      \u6570\u636e\u8303\u56f4: 2025-01-02 00:00:00 to 2025-05-22 00:00:00
      \u4ea4\u6613\u5929\u6570: 97<\/pre>\n\n\n\n
        \n
      • \u4ef7\u683c\u8d70\u52bf<\/strong>\uff1aTSLA\u80a1\u4ef7\u4ece1\u6708\u521d\u7684400\u7f8e\u5143\u8dcc\u52303\u6708\u4e2d\u65ec\u7684250\u7f8e\u5143\uff0c\u968f\u540e\u57284\u6708\u4e2d\u65ec\u53cd\u5f39\u81f3350\u7f8e\u5143\u3002<\/li>\n\n\n\n
      • \u8d8b\u52bf\u659c\u7387<\/strong>\uff1a3\u6708\u4e2d\u65ec\u81f34\u6708\u521d\uff0c\u659c\u7387\u4e3a\u8d1f\uff0c\u8868\u660e\u4e0b\u8dcc\u8d8b\u52bf\uff1b4\u6708\u521d\u540e\u8f6c\u4e3a\u6b63\uff0c\u663e\u793a\u4e0a\u6da8\u8d8b\u52bf\u3002<\/li>\n\n\n\n
      • \u52a0\u901f\u5ea6<\/strong>\uff1a4\u6708\u521d\uff0c\u52a0\u901f\u5ea6\u4ece\u8d1f\u8f6c\u6b63\uff0c\u5e76\u57284\u6708\u4e2d\u65ec\u8fbe\u5230\u5cf0\u503c\uff08\u7ea60.15\uff09\uff0c\u89e6\u53d1\u4e70\u5165\u4fe1\u53f7\u3002<\/li>\n\n\n\n
      • \u6295\u8d44\u7ec4\u5408\u4ef7\u503c<\/strong>\uff1a\u521d\u59cb\u8d44\u91d110,000\u7f8e\u5143\uff0c\u57284\u6708\u4e2d\u65ec\u4e70\u5165\u540e\uff0c\u8d44\u91d1\u6da8\u81f3\u7ea613,000\u7f8e\u5143\uff0c\u6536\u76ca\u738725.35%\u3002<\/li>\n<\/ul>\n\n\n\n
        \u76f8\u6bd4\u4e4b\u4e0b\uff0c\u4e70\u5165\u6301\u6709\u7b56\u7565\u4ece400\u7f8e\u5143\u8dcc\u5230350\u7f8e\u5143\uff0c\u6536\u76ca\u7387-10.08% \u3002\u8d8b\u52bf\u52a0\u901f\u5ea6\u7b56\u7565\u6210\u529f\u6355\u6349\u4e863\u6708\u4e2d\u65ec\u7684\u4f4e\u70b9\uff0c\u5e76\u5728\u4e0a\u6da8\u4e2d\u83b7\u5229\u3002<\/p>\n\n\n\n
        \u6027\u80fd\u5bf9\u6bd4\u8868<\/strong>\uff1a<\/p>\n\n\n\n
        \u7b56\u7565<\/th>\u65f6\u95f4\u8303\u56f4<\/th>\u6536\u76ca\u7387<\/th><\/tr><\/thead>
        \u4e70\u5165\u6301\u6709<\/td>2025-01-01 ~ 2025-05-23<\/td>– 10.08%<\/td><\/tr>
        \u8d8b\u52bf\u52a0\u901f\u5ea6\u7b56\u7565<\/td>2025-01-01 ~ 2025-05-23<\/td>+ 25.35%<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n
        \u4e0b\u9762\u7684\u56db\u5f20\u5b50\u56fe\uff0c\u5206\u522b\u5bf9\u5e94TSLA\u4ef7\u683c\u8d70\u52bf\u3001\u8d8b\u52bf\u659c\u7387\u3001\u52a0\u901f\u5ea6\u548c\u6295\u8d44\u7ec4\u5408\u4ef7\u503c\uff1a<\/p>\n\n\n\n
        \"\"<\/figure>\n\n\n\n

        \u4e09\u3001\u624b\u628a\u624b\u4ee3\u7801\u6559\u5b66<\/strong><\/h2>\n\n\n\n
        \u6211\u6765\u5e26\u4f60\u4e00\u6b65\u6b65\u5b9e\u73b0\u4e0a\u9762\u7684\u7b56\u7565\u91cf\u5316\u3002\u4ee5\u4e0b\u662f\u5173\u952e\u4ee3\u7801\u6b65\u9aa4\uff0c\u4f60\u53ef\u4ee5\u5728\u672c\u5730\u6216\u4e91\u7aef\uff08\u5982Jupyter Notebook\uff09\u8fd0\u884c\u3002<\/p>\n\n\n\n
        \u6b65\u9aa41\uff1a\u83b7\u53d6\u6570\u636e\uff085\u884c\u4ee3\u7801\u641e\u5b9a\uff09<\/strong><\/h3>\n\n\n\n
        # \u5b89\u88c5\u5e93\uff08\u5df2\u5b89\u88c5\u53ef\u8df3\u8fc7\uff09\n!pip install yfinance pandas -q  \n\n# \u83b7\u53d6\u7279\u65af\u62c92025\u5e74\u6570\u636e\uff08\u5b9e\u9645\u4f7f\u7528\u65f6\u66ff\u6362\u4e3a\u5f53\u524d\u65e5\u671f\uff09\nimport yfinance as yf\ndata = yf.download('TSLA', start='2025-01-01', end='2025-05-25')\nprint(data.head())  # \u67e5\u770b\u524d5\u884c<\/code><\/pre>\n\n\n\n
        \u6b65\u9aa42\uff1a\u8ba1\u7b97\u8d8b\u52bf\u52a0\u901f\u5ea6\uff08\u6838\u5fc3\u7b97\u6cd5\uff09<\/strong><\/h3>\n\n\n\n
        from scipy import stats\nimport numpy as np\n\ndef \u8ba1\u7b97\u52a0\u901f\u5ea6(\u6536\u76d8\u4ef7, \u8d8b\u52bf\u7a97\u53e3=50, \u52a0\u901f\u7a97\u53e3=5):\n    # \u7b2c\u4e00\u6b65\uff1a\u8ba1\u7b97\u8d8b\u52bf\u659c\u7387\uff08\u7269\u7406\u4e2d\u7684\"\u901f\u5ea6\"\uff09\n    \u8d8b\u52bf\u659c\u7387 = \u6536\u76d8\u4ef7.rolling(\u8d8b\u52bf\u7a97\u53e3).apply(\n        lambda x: stats.linregress(np.arange(len(x)), x).slope\n    )\n    \n    # \u7b2c\u4e8c\u6b65\uff1a\u8ba1\u7b97\u659c\u7387\u7684\u659c\u7387\uff08\u7269\u7406\u4e2d\u7684\"\u52a0\u901f\u5ea6\"\uff09\n    \u52a0\u901f\u5ea6 = \u8d8b\u52bf\u659c\u7387.rolling(\u52a0\u901f\u7a97\u53e3).apply(\n        lambda x: stats.linregress(np.arange(len(x)), x).slope\n    )\n    return \u8d8b\u52bf\u659c\u7387, \u52a0\u901f\u5ea6<\/code><\/pre>\n\n\n\n
        \u6b65\u9aa43\uff1a\u751f\u6210\u4e70\u5356\u4fe1\u53f7<\/strong><\/h3>\n\n\n\n
        # \u4fe1\u53f7\u89c4\u5219\u8868\uff08\u5efa\u8bae\u6536\u85cf\uff09\n| \u4fe1\u53f7\u7c7b\u578b | \u89e6\u53d1\u6761\u4ef6                     | \u5b9e\u6218\u6848\u4f8b          |\n|----------|------------------------------|-------------------|\n| \u4e70\u5165     | \u52a0\u901f\u5ea6>0 & \u8d8b\u52bf\u659c\u7387<0         | \u7279\u65af\u62c93\u670825\u65e5\u89e6\u53d1 |\n| \u5356\u51fa     | \u52a0\u901f\u5ea6<-0.01 & \u8d8b\u52bf\u659c\u7387>0     | \u5b81\u5fb7\u65f6\u4ee34\u670818\u65e5\u89e6\u53d1 |\n\n# \u907f\u514d\u5047\u4fe1\u53f7\uff01\u5fc5\u987b\u540c\u6b65\u6ee1\u8db3\uff1a\n# 1. \u6536\u76d8\u4ef7\u7ad9\u4e0a5\u65e5\u5747\u7ebf\n# 2. \u6210\u4ea4\u91cf\u8f83\u524d\u65e5\u653e\u592750%:cite<\/code><\/pre>\n\n\n\n
        \u6b65\u9aa4\u56db\uff1a\u56de\u6d4b\u7b56\u7565<\/strong><\/h3>\n\n\n\n
        def backtest(data, signals):\n    position = 0\n    cash = 10000\n    holdings = 0\n    portfolio = []\n    for i in range(len(data)):\n        if signals[i] == 1:\n            holdings = cash \/ data[i]\n            cash = 0\n            position = 1\n        elif signals[i] == -1:\n            cash = holdings * data[i]\n            holdings = 0\n            position = 0\n        portfolio_value = cash + holdings * data[i]\n        portfolio.append(portfolio_value)\n    return pd.Series(portfolio, index=data.index)<\/code><\/pre>\n\n\n\n
        \u6b65\u9aa4\u4e94\uff1a\u7ed8\u5236\u56fe\u50cf\u7ed3\u679c<\/strong><\/h3>\n\n\n\n
        def plot_results(stock_data):\n    plt.figure(figsize=(14, 12))\n\n    # \u5e26\u4fe1\u53f7\u7684\u4ef7\u683c\n    plt.subplot(4, 1, 1)\n    plt.plot(stock_data['Close'], label='Price', alpha=0.7)\n\n    #\u7bc7\u5e45\u5173\u7cfb\uff0c\u8be6\u89c1\u5b8c\u6574\u4ee3\u7801\u3002\u3002\u3002\n\n    # \u6295\u8d44\u7ec4\u5408\u4ef7\u503c\n    plt.subplot(4, 1, 4)\n    plt.plot(stock_data['Portfolio_Value'], label='Portfolio Value', color='blue')\n    plt.title('Portfolio Value Over Time')\n    plt.legend()\n\n    plt.tight_layout()\n    plt.show() <\/code><\/pre>\n\n\n\n
        \u56db\u3001\u7b56\u7565\u4f18\u52bf\u4e0e\u6ce8\u610f\u4e8b\u9879<\/strong><\/h2>\n\n\n\n

        4.1 \u4f18\u52bf<\/strong><\/h3>\n\n\n\n