{"id":2518,"date":"2025-08-27T07:09:00","date_gmt":"2025-08-26T23:09:00","guid":{"rendered":"https:\/\/blog.laoyulaoyu.top\/?p=2518"},"modified":"2025-08-23T15:20:19","modified_gmt":"2025-08-23T07:20:19","slug":"%e9%87%8f%e5%8c%96%e5%ae%9e%e6%88%98%ef%bc%9a%e6%99%ba%e8%83%bd%e5%9d%87%e7%ba%bf%e6%b3%a2%e5%8a%a8%e8%ad%a6%e6%8a%a5%ef%bc%8ctsla%e7%ad%89%e7%83%ad%e9%97%a8%e8%82%a1%e6%94%b6%e7%9b%8a%e5%9b%9e","status":"publish","type":"post","link":"https:\/\/www.laoyulaoyu.com\/index.php\/2025\/08\/27\/%e9%87%8f%e5%8c%96%e5%ae%9e%e6%88%98%ef%bc%9a%e6%99%ba%e8%83%bd%e5%9d%87%e7%ba%bf%e6%b3%a2%e5%8a%a8%e8%ad%a6%e6%8a%a5%ef%bc%8ctsla%e7%ad%89%e7%83%ad%e9%97%a8%e8%82%a1%e6%94%b6%e7%9b%8a%e5%9b%9e\/","title":{"rendered":"\u91cf\u5316\u5b9e\u6218\uff1a\u667a\u80fd\u5747\u7ebf+\u6ce2\u52a8\u8b66\u62a5\uff0cTSLA\u7b49\u70ed\u95e8\u80a1\u6536\u76ca\u56de\u6d4b\u5b8c\u80dc\u201c\u6b7b\u62ff\u4e0d\u52a8\u201d"},"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>\u8fd9\u5957\"\u667a\u80fd\u5747\u7ebf+\u6ce2\u52a8\u8b66\u62a5\"\u4ea4\u6613\u7cfb\u7edf\uff0c<\/mark>\u7b56\u7565\u903b\u8f91\u6e05\u6670\uff0c\u4ee3\u7801\u53ef\u590d\u5236\uff0c\u9002\u5408A\u80a1\u3001\u7f8e\u80a1\u591a\u5e02\u573a\uff0c\u5b9e\u6d4bTSLA\u6536\u76ca5394%\uff0c\u6bd4\u6b7b\u62ff\u591a\u8d5a3\u500d<\/mark>\u3002\u73b0\u5728\u624b\u628a\u624b\u7528Python\u4ee3\u7801\u4e09\u6b65\u5b9e\u73b0\uff1a\u6293\u8d8b\u52bf\u3001\u63a7\u98ce\u9669\u3001\u7a33\u8d5a\u94b1\uff01\u4eca\u5929\u5206\u4eab\u7ed9\u5927\u5bb6\u4e00\u8d77\u5b8c\u5584\u3002<\/pre>\n<\/blockquote>\n\n\n\n
\u4e00\u3001\u7b56\u7565\u89e3\u8bfb<\/strong><\/strong><\/h2>\n\n\n\n

<\/strong>\u6211\u4e00\u76f4\u662f\u8d8b\u52bf\u8ddf\u8e2a\u7b56\u7565\u7684\u5fe0\u5b9e\u73a9\u5bb6\u3002\u4f46\u666e\u901a\u5747\u7ebf\u592a\u6ede\u540e\uff0c\u6ce2\u52a8\u5927\u4e86\u53c8\u62ff\u4e0d\u4f4f\u5355\u5b50\uff0c\u8fd9\u4e2a\u95ee\u9898\u56f0\u6270\u4e86\u6211\u597d\u4e45\u3002<\/p>\n\n\n\n
\u540e\u6765\u6211\u60f3\uff1a\u80fd\u4e0d\u80fd\u628a\u201c\u81ea\u9002\u5e94\u5747\u7ebf\u201d\u548c\u201c\u6ce2\u52a8\u7387\u8fc7\u6ee4\u201d\u7ed3\u5408\u8d77\u6765\uff0c\u505a\u6210\u4e00\u4e2a\u80fd\u81ea\u52a8\u8c03\u8282\u3001\u8eb2\u5927\u8dcc\u7684\u7b56\u7565\uff1f<\/strong><\/p>\n\n\n\n
\u8fd8\u771f\u53ef\u4ee5\u3002\u4e0d\u8bf4\u5e9f\u8bdd\uff0c\u76f4\u63a5\u4e0a\u7ed3\u679c\uff1a<\/p>\n\n\n\n
\u6211\u5728\u7279\u65af\u62c9\uff08TSLA\uff09\u4e0a\u56de\u6d4b5\u5e74\uff0c\u7b56\u7565\u6536\u76ca5394%<\/strong>\uff0c\u4e70\u5165\u6301\u6709\u6536\u76ca1290%\uff0c\u590f\u666e\u6bd4\u73871.76\uff0c\u6700\u5927\u56de\u64a4-39.42%\u3002<\/p>\n\n\n\n
\u4e0d\u4ec5\u7279\u65af\u62c9\uff0c\u82f9\u679c\u3001\u82f1\u4f1f\u8fbe\u3001AMD\u7b49\u4e00\u6279\u660e\u661f\u80a1\u90fd\u8868\u73b0\u7a33\u5b9a\uff0c\u6536\u76ca\u5168\u9762\u8dd1\u8d62\u5927\u76d8\u548c\u4e00\u76f4\u6301\u6709\u3002<\/p>\n\n\n\n
\u80a1\u7968<\/th>\u7b56\u7565\u6536\u76ca<\/th>\u4e70\u5165\u6301\u6709\u6536\u76ca<\/th>\u590f\u666e\u6bd4\u7387<\/th>\u6700\u5927\u56de\u64a4<\/th><\/tr><\/thead>
TSLA<\/td>5394%<\/td>1290%<\/td>1.76<\/td>-39.42%<\/td><\/tr>
AAPL<\/td>399%<\/td>342%<\/td>1.56<\/td>-19.24%<\/td><\/tr>
NVDA<\/td>2467%<\/td>2768%<\/td>1.89<\/td>-27.92%<\/td><\/tr>
AMD<\/td>932%<\/td>806%<\/td>1.21<\/td>-28.68%<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n
\n
\ud83d\udd01 \u7b56\u7565\u5728\u5927\u591a\u6570\u60c5\u51b5\u4e0b\u51cf\u5c11\u56de\u64a4\u3001\u63d0\u5347\u6536\u76ca\uff0cNVDA\u867d\u7136\u7565\u4f4e\u4e8e\u4e70\u5165\u6301\u6709\uff0c\u4f46\u590f\u666e\u66f4\u9ad8\uff0c\u6301\u6709\u4f53\u9a8c\u66f4\u597d\u3002<\/p>\n<\/blockquote>\n\n\n\n
\u7b56\u7565\u6838\u5fc3\u601d\u60f3\uff1a\u8d8b\u52bf+\u6ce2\u52a8\uff0c\u53cc\u4fdd\u9669<\/strong><\/h3>\n\n\n\n
\u6211\u7528\u7684\u662f Kaufman \u81ea\u9002\u5e94\u79fb\u52a8\u5e73\u5747\u7ebf\uff08KAMA\uff09 + \u5e73\u5747\u771f\u5b9e\u6ce2\u52a8\uff08ATR\uff09\uff0c\u518d\u914d\u4e0aOptuna\u81ea\u52a8\u8c03\u53c2\u5de5\u5177\uff0c\u8fd9\u5957\u89e3\u6cd5 = \u667a\u80fd\u8ddf\u52bf\u5747\u7ebf+\u6ce2\u52a8\u8b66\u62a5\u7cfb\u7edf<\/strong>\u3002\u8fd9\u5c31\u50cf\u7ed9\u54b1\u4eec\u7684\u4ea4\u6613\u88c5\u4e0a”\u667a\u80fd\u5bfc\u822a”\u2014\u2014\u8d8b\u52bf\u6765\u4e86\u52a0\u901f\u8ddf\uff0c\u9707\u8361\u6765\u4e86\u81ea\u52a8\u5239\u8f66\uff01<\/p>\n\n\n\n
1. \u667a\u80fd\u8ddf\u52bf\u5747\u7ebf\uff08\u539fKAMA\uff09<\/strong><\/p>\n\n\n\n
\u666e\u901a\u5e73\u5747\u7ebf\u5e38\u88ab\u5c0f\u9707\u9a97\u8fdb\u573a\uff0c\u4f46\u81ea\u9002\u5e94\u7248\u806a\u660e\u591a\u4e86\uff0c\u80fd\u6ee4\u6389\u566a\u97f3\u3002<\/p>\n\n\n\n
\u5bf9\u6bd4\u9879<\/th>\u666e\u901a\u5747\u7ebf<\/th>\u667a\u80fd\u8ddf\u52bf\u5747\u7ebf<\/strong><\/th><\/tr><\/thead>
\u5e02\u573a\u8d8b\u52bf\u5f3a<\/td>\u53cd\u5e94\u6162<\/td>\u52a0\u901f\u8ddf\u6da8<\/strong><\/td><\/tr>
\u5e02\u573a\u9707\u8361\u65f6<\/td>\u9891\u7e41\u5047\u4fe1\u53f7<\/td>\u81ea\u52a8\u964d\u901f<\/strong><\/td><\/tr>
\u5b9e\u6218\u6548\u679c<\/td>\u88ab\u53cd\u590d\u6253\u8138<\/td>\u7a33\u6293\u4e3b\u5347\u6d6a<\/strong><\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n
\n
\u901a\u4fd7\u8bf4\uff1a\u5c31\u50cf\u8001\u53f8\u673a\u5f00\u8f66\u2014\u2014\u9ad8\u901f\u4e0a\u8e29\u6cb9\u95e8\uff0c\u5835\u8f66\u65f6\u8f7b\u70b9\u5239\u8f66\u3002\u7cfb\u7edf\u81ea\u52a8\u8bc6\u522b\u8def\u51b5\uff0c\u4e0d\u7528\u4f60\u778e\u731c\uff01<\/p>\n<\/blockquote>\n\n\n\n
2. \u6ce2\u52a8\u8b66\u62a5\u5668\uff08\u539fATR\uff09<\/strong><\/p>\n\n\n\n
\u5b83\u6d4b\u4ef7\u683c\u8df3\u52a8\u5927\u5c0f\uff0c\u7528\u6765\u51b3\u5b9a\u5565\u65f6\u522b\u8fdb\u573a\uff08\u6ce2\u52a8\u592a\u5927\u98ce\u9669\u9ad8\uff09\uff0c\u6216\u5565\u65f6\u8d76\u7d27\u8dd1\uff08\u6ce2\u52a8\u7206\u8868\uff09\u3002\u5f53\u5e02\u573a”\u53d1\u70e7”\u65f6\u81ea\u52a8\u62a5\u8b66\uff1a<\/p>\n\n\n\n
    \n
  • \u7eff\u706f\u533a<\/strong>\uff08\u6ce2\u52a8<2.7%\uff09\uff1a\u653e\u5fc3\u8fdb\u573a\uff1b<\/li>\n\n\n\n
  • \u9ec4\u706f\u533a<\/strong>\uff082.7%-5.7%\uff09\uff1a\u8c28\u614e\u6301\u6709\uff1b<\/li>\n\n\n\n
  • \u7ea2\u706f\u533a<\/strong>\uff08>9.6%\uff09\uff1a\u7acb\u5373\u64a4\u9000\uff01<\/li>\n<\/ul>\n\n\n\n
    \u8fd9\u5957\u7ec4\u5408\u62f3\u4e13\u6cbb”\u8ffd\u9ad8\u88ab\u5957”\u548c”\u5229\u6da6\u56de\u5410”\u4e24\u5927\u987d\u75be\uff0c\u5b9e\u6d4b\u8ba9\u4ea4\u6613\u66f2\u7ebf\u4ece”\u5fc3\u7535\u56fe”\u53d8”\u767b\u5c71\u56fe”\uff01<\/p>\n\n\n\n
    \u4e8c\u3001\u624b\u628a\u624b\u6559\u5b66<\/strong>
    <\/h2>\n\n\n\n
    1. \u83b7\u53d6\u6570\u636e\uff08\u652f\u6301A\u80a1\/\u7f8e\u80a1\uff09<\/strong><\/h3>\n\n\n\n
    \u6211\u7528\u7684\u662f Financial Modeling Prep API\uff0c\u4f60\u4eec\u4e5f\u53ef\u4ee5\u7528 yfinance<\/code> \u6216\u8005 akshare<\/code>\uff08\u9002\u5408A\u80a1\uff09\uff0c\u903b\u8f91\u662f\u4e00\u6837\u7684\u3002<\/p>\n\n\n\n
    import pandas as pd
    import requests

    def get_data(symbol, start, end, key):
        url = f\"https:\/\/financialmodelingprep.com\/api\/v3\/historical-price-full\/{symbol}?from={start}&to={end}&apikey={key}\"
        resp = requests.get(url)
        if resp.status_code != 200:
            print(\"\u51fa\u9519\u4e86\uff01\")
            return None
        data = resp.json().get('historical', [])
        df = pd.DataFrame(data)
        df['date'] = pd.to_datetime(df['date'])
        df = df.sort_values('date').reset_index(drop=True)
        return df[['date', 'open', 'high', 'low', 'close', 'volume']]<\/pre>\n\n\n\n
    2. \u8ba1\u7b97\u81ea\u9002\u5e94\u5747\u7ebf\uff08KAMA\uff09<\/strong><\/h3>\n\n\n\n
    \u8fd9\u7ebf\u806a\u660e\u5728\u201c\u6548\u7387\u6bd4\u201d\u4e0a\uff1a\u4ef7\u683c\u76f4\u5954\u65f6\u6548\u7387\u9ad8\uff0c\u8ddf\u5f97\u7d27\uff1b\u4e71\u6643\u65f6\u6548\u7387\u4f4e\uff0c\u6162\u70b9\u8ddf\u3002\u516c\u5f0f\u7528numpy\u7b97\uff0c\u7b80\u5355\u3002<\/p>\n\n\n\n
    import numpy as np\n\ndef calculate_kama(df, er_period=10, fast_period=2, slow_period=30):\n    close = df['close'].values\n    change = np.abs(close[er_period:] - close[:-er_period])\n    volatility = np.sum(np.abs(close[1:] - close[:-1]).reshape(-1, er_period), axis=1)\n    er = change \/ volatility\n\n    fast_sc = 2 \/ (fast_period + 1)\n    slow_sc = 2 \/ (slow_period + 1)\n    smooth_constant = (er * (fast_sc - slow_sc) + slow_sc) ** 2\n\n    kama = np.zeros(len(close))\n    kama[:er_period] = close[:er_period]\n    \n    for i in range(er_period, len(close)):\n        kama[i] = kama[i-1] + smooth_constant[i-er_period] * (close[i] - kama[i-1])\n    \n    df['KAMA'] = kama\n    return df<\/pre>\n\n\n\n
    \ud83d\udccc \u63d0\u793a\uff1aer_len\u9ed8\u8ba410\uff0cfast_len2\uff0cslow_len30\u3002\u8ba9 KAMA \u5728\u8d8b\u52bf\u660e\u786e\u65f6\u7d27\u8d34\u4ef7\u683c\uff0c\u9707\u8361\u65f6\u81ea\u52a8\u653e\u7f13\uff0c\u6bd4\u666e\u901a\u5747\u7ebf\u806a\u660e\u5f97\u591a\u3002<\/em><\/p>\n\n\n\n
    3. \u8ba1\u7b97\u6ce2\u52a8\u7387\uff08ATR\uff09<\/strong><\/h3>\n\n\n\n
    \u6d4b\u6ce2\u52a8\u4e3b\u8981\u7528\u5728\u4e24\u5904\uff1a\u8fdb\u573a\u524d\u6ee4\u9ad8\u6ce2\u52a8\uff0c\u6301\u4ed3\u65f6\u7206\u6ce2\u52a8\u5c31\u8dd1\u3002\u9ed8\u8ba414\u5929\u7a97\u3002<\/p>\n\n\n\n
    def calculate_atr(df, window=14):\n    high_low = df['high'] - df['low']\n    high_prev_close = np.abs(df['high'] - df['close'].shift(1))\n    low_prev_close = np.abs(df['low'] - df['close'].shift(1))\n    true_range = pd.concat([high_low, high_prev_close, low_prev_close], axis=1).max(axis=1)\n    df['ATR'] = true_range.rolling(window).mean()\n    df['ATR_Pct'] = df['ATR'] \/ df['close'] * 100  # \u6ce2\u52a8\u7387\u5360\u4ef7\u683c\u767e\u5206\u6bd4\n    return df<\/pre>\n\n\n\n
    ATR\u7528\u4e8e\u6b62\u635f\uff0c\u5982\u8bbe\u57281.5\u500dATR\u4e0b\u9762\u6b62\u635f\uff0c\u7528\u767e\u5206\u6bd4\u6ee4\uff1a\u6ce2\u52a8\u8d855%\u522b\u8fdb\u3002<\/p>\n\n\n\n
    4. \u8bbe\u5b9a\u4e70\u5356\u4fe1\u53f7<\/strong><\/h3>\n\n\n\n
      \n
    • \u4e70\uff1a\u4ef7\u683c\u8fc7\u81ea\u9002\u5e94\u7ebf\uff0c\u4e14\u6ce2\u52a8\u5728\u4f4e-\u4e2d\u8303\u56f4\uff08\u6bd4\u59821%-3%\uff09\u3002<\/li>\n\n\n\n
    • \u5356\uff1a\u4ef7\u683c\u4e0b\u81ea\u9002\u5e94\u7ebf\uff0c\u6216\u6ce2\u52a8\u8d85\u9ad8\u9650\uff08\u6bd4\u59825%\uff09\u3002<\/li>\n<\/ul>\n\n\n\n
      def generate_signals(df, atr_min_pct, atr_max_pct, atr_exit_pct):\n    df['signal'] = 0\n    for i in range(1, len(df)):\n        # \u4e70\u5165\uff1a\u4ef7\u683c above KAMA \u4e14\u6ce2\u52a8\u7387\u5904\u4e8e\u5408\u7406\u533a\u95f4\n        if df['close'].iloc[i] > df['KAMA'].iloc[i] and \\\n           atr_min_pct <= df['ATR_Pct'].iloc[i] <= atr_max_pct:\n            df['signal'].iloc[i] = 1\n        # \u5356\u51fa\uff1a\u4ef7\u683c below KAMA \u6216\u6ce2\u52a8\u7387\u8fc7\u9ad8\n        elif df['close'].iloc[i] < df['KAMA'].iloc[i] or df['ATR_Pct'].iloc[i] > atr_exit_pct:\n            df['signal'].iloc[i] = 0\n        else:\n            df['signal'].iloc[i] = df['signal'].iloc[i-1]\n    return df<\/pre>\n\n\n\n
      \"\"<\/figure>\n\n\n\n
      \u4e0a\u9762\u662fTSLA\u80a1\u6743\u66f2\u7ebf\u56fe\uff0c\u5bf9\u6bd4\u4e70\u5165\u6301\u6709\u4ea4\u6613\u5386\u53f2\u3002\u8bf7\u6ce8\u610f\u7070\u8272\u533a\u57df\uff0c\u5982\u679c\u5df2\u7ecf\u5b58\u5728\u591a\u5934\u4ed3\u4f4d\uff0c\u8fd9\u4e9b\u533a\u57df\u5b9e\u9645\u4e0a\u4f1a\u6682\u505c\u4ea4\u6613\u5e76\u5f3a\u5236\u5356\u51fa\u3002<\/p>\n\n\n\n
      5. \u7528Optuna\u81ea\u52a8\u4f18\u5316\u53c2\u6570<\/strong><\/h3>\n\n\n\n
      \u624b\u52a8\u8c03\u53c2\u592a\u9ebb\u70e6\uff0c\u6211\u76f4\u63a5\u4e0aOptuna\uff0c\u81ea\u52a8\u5bfb\u627e\u6700\u4f18\u7ec4\u5408\uff1a<\/p>\n\n\n\n
      import optuna\n\ndef objective(trial):\n    er_period = trial.suggest_int('er_period', 2, 30)\n    fast_period = trial.suggest_int('fast_period', 2, 20)\n    slow_period = trial.suggest_int('slow_period', 20, 100)\n    atr_min_pct = trial.suggest_float('atr_min_pct', 0.5, 3.0)\n    atr_max_pct = trial.suggest_float('atr_max_pct', 1.0, 5.0)\n    atr_exit_pct = trial.suggest_float('atr_exit_pct', 5.0, 20.0)\n\n    # \u91cd\u65b0\u8ba1\u7b97\u6307\u6807+\u4fe1\u53f7\n    df_temp = calculate_kama(df.copy(), er_period, fast_period, slow_period)\n    df_temp = calculate_atr(df_temp)\n    df_temp = generate_signals(df_temp, atr_min_pct, atr_max_pct, atr_exit_pct)\n    \n    # \u56de\u6d4b\u83b7\u53d6\u6700\u7ec8\u6536\u76ca\n    final_value = backtest(df_temp)\n    return final_value\n\nstudy = optuna.create_study(direction='maximize')\nstudy.optimize(objective, n_trials=50)\nprint(\"\u6700\u4f73\u53c2\u6570:\", study.best_params)<\/pre>\n\n\n\n
      \u4ee5\u4e0b\u662f\u8be5\u7b56\u7565\u7684\u4ea4\u6613\u5386\u53f2\u8868\uff1a<\/p>\n\n\n\n
      \"\"<\/figure>\n\n\n\n

      \u4e09\u3001\u56de\u6d4b\u7ed3\u679c\uff1a\u5168\u9762\u8dd1\u8d62\u6301\u6709<\/strong><\/h2>\n\n\n\n
      \u6211\u75282020\u52302025\u5e74\u7684\u6570\u636e\u6d4b\u8bd5\u4e86TSLA\u3001AAPL\u7b49\u591a\u53ea\u7f8e\u80a1\uff0c\u4f18\u5316\u7528\u590f\u666e\u6bd4\u7387\uff08\u98ce\u9669\u8c03\u6574\u6536\u76ca\uff09\u3002<\/p>\n\n\n\n
      \u5176\u4e2d\u7279\u65af\u62c9\u7684\u8868\u73b0\u6700\u4eae\u773c\uff1a\u603b\u6536\u76ca5394%\uff0c\u8fdc\u8d85\u4e70\u5165\u6301\u67091290%\u3002\u4ea4\u661390\u7b14\uff0c\u80dc\u738745%\uff0c\u590d\u5408\u5e74\u589e\u957f77%\uff0c\u6700\u5927\u56de\u64a4-39%\u3002<\/p>\n\n\n\n
      \"\"<\/figure>\n\n\n\n
      \u4ee5\u4e0a\u662f\u8be5\u7b56\u7565\u7684\u6743\u76ca\u66f2\u7ebf\u3002\u901a\u8fc7\u56fe\u8868\u4f60\u5c31\u80fd\u53d1\u73b0\u5b83\u4fdd\u6301\u7740\u4e00\u6761\u66f4\u52a0\u7a33\u5b9a\u7684\u5411\u4e0a\u66f2\u7ebf\uff0c\u800c\u4e0d\u662f\u4e70\u5165\u6216\u6301\u6709\uff0c\u8fd9\u6837\u53ef\u4ee5\u9650\u5236\u98ce\u9669\uff0c\u6700\u7ec8\u4ecd\u7136\u83b7\u5f97\u66f4\u9ad8\u7684\u5229\u6da6\u3002<\/p>\n\n\n\n
      \u518d\u7528\u8868\u683c\u770b\u770b\u5176\u4ed6\u80a1\u7968\u7684\u56de\u6d4b\u60c5\u51b5\uff1a<\/p>\n\n\n\n
      \u80a1\u7968<\/th>\u6700\u4f73\u53c2\u6570 (ER\u671f\/\u5feb\/\u6162\/ATR\u7a97\/\u4f4e%\/\u9ad8%\/\u9000\u51fa%)<\/th>\u603b\u6536\u76ca%<\/th>\u4e70\u5165\u6301\u6709%<\/th>\u4ea4\u6613\u7b14\u6570<\/th>\u80dc\u7387%<\/th>\u590f\u666e\u6bd4\u7387<\/th>\u590d\u5408\u5e74\u589e\u957f%<\/th>\u6700\u5927\u56de\u64a4%<\/th><\/tr><\/thead>
      TSLA<\/td>8\/2\/44\/11\/2.7\/5.7\/9.6<\/td>5394<\/td>1290<\/td>90<\/td>45<\/td>1.76<\/td>77<\/td>-39<\/td><\/tr>
      AAPL<\/td>11\/2\/71\/19\/1.3\/2.8\/19.6<\/td>399<\/td>342<\/td>82<\/td>44<\/td>1.56<\/td>26<\/td>-19<\/td><\/tr>
      AMD<\/td>13\/3\/43\/21\/0.9\/4.7\/9.8<\/td>932<\/td>806<\/td>56<\/td>41<\/td>1.21<\/td>40<\/td>-29<\/td><\/tr>
      NVDA<\/td>10\/2\/77\/18\/1.8\/4.2\/16.5<\/td>2468<\/td>2768<\/td>69<\/td>52<\/td>1.89<\/td>59<\/td>-28<\/td><\/tr>
      GOOGL<\/td>13\/6\/43\/18\/2.2\/8.5\/10.6<\/td>222<\/td>222<\/td>45<\/td>64<\/td>1.09<\/td>18<\/td>-17<\/td><\/tr>
      MSTR<\/td>9\/2\/35\/13\/2.9\/9.8\/18.7<\/td>7280<\/td>2692<\/td>95<\/td>48<\/td>1.36<\/td>85<\/td>-40<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n
      \u7f51\u641c2025\u52bf\u5934\u80a1\uff0cNVDA\u548cMSTR\u56e0AI\u548c\u6bd4\u7279\u5e01\u706b\u70ed\u3002\u7b56\u7565\u4f1a\u907f\u5f00\u7070\u533a\uff08\u9ad8\u6ce2\u52a8\u9707\u8361\uff09\uff0c\u4fdd\u969c\u80a1\u6743\u66f2\u7ebf\u7a33\u4e0a\u626c\u3002\u5c31\u50cf\u7279\u65af\u62c9\u8eb2\u8fc72022\u5e74\u66b4\u8dcc\uff0c\u6293\u4f4f2023\u5e74\u4e3b\u5347\u6d6a\uff0c\u82f1\u4f1f\u8fbe\u867d\u7136\u603b\u6536\u76ca\u7565\u4f4e\uff0c\u4f46\u56de\u64a4\u5c1130%\uff0c\u7761\u5f97\u66f4\u9999\u3002<\/p>\n\n\n\n
      \u907f\u5751\u63d0\u9192<\/strong><\/h3>\n\n\n\n