{"id":4951,"date":"2026-09-29T07:42:00","date_gmt":"2026-09-28T23:42:00","guid":{"rendered":"https:\/\/laoyulaoyu.com\/?p=4951"},"modified":"2026-09-19T23:51:23","modified_gmt":"2026-09-19T15:51:23","slug":"%e6%8a%8a%e7%ad%94%e6%a1%88%e6%89%93%e4%b9%b1%e5%96%82%e7%bb%99%e6%a8%a1%e5%9e%8b%ef%bc%8c%e5%ae%83%e7%85%a7%e6%a0%b7%e5%87%86%e7%a1%ae%e7%8e%87-55","status":"publish","type":"post","link":"https:\/\/laoyulaoyu.com\/index.php\/2026\/09\/29\/%e6%8a%8a%e7%ad%94%e6%a1%88%e6%89%93%e4%b9%b1%e5%96%82%e7%bb%99%e6%a8%a1%e5%9e%8b%ef%bc%8c%e5%ae%83%e7%85%a7%e6%a0%b7%e5%87%86%e7%a1%ae%e7%8e%87-55\/","title":{"rendered":"\u628a\u7b54\u6848\u6253\u4e71\u5582\u7ed9\u6a21\u578b\uff0c\u5b83\u7167\u6837\u51c6\u786e\u7387 55%"},"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

\u6587\u4e2d\u793a\u4f8b\u4ec5\u7528\u4e8e\u6280\u672f\u8ba8\u8bba\uff0c\u4e0d\u6784\u6210\u4efb\u4f55\u64cd\u4f5c\u5efa\u8bae\u3002
\u91cf\u5316\u7b56\u7565\u5f00\u53d1\u5e94\u4ee5\u5b66\u4e60\u548c\u6280\u672f\u4ea4\u6d41\u4e3a\u76ee\u7684\u3002
\u672c\u53f7\u4e0d\u8350\u80a1\u3001\u4e0d\u5356\u8bfe\u3001\u4e0d\u627f\u8bfa\u6536\u76ca\u3002
\u5e02\u573a\u6709\u98ce\u9669\uff0c\u8bf7\u5408\u6cd5\u5408\u89c4\u6295\u8d44\u3002<\/p>\n<\/blockquote>\n\n\n\n

\u672c\u6587\u7ea6 2500 \u5b57 | \u9884\u8ba1\u9605\u8bfb 8 \u5206\u949f\uff0c\u524d\u534a\u662f\u6211\u81ea\u5df1\u8dd1\u51fa\u6765\u7684\u6570\u5b57\uff0c\u540e\u534a\u6709\u53ef\u4ee5\u76f4\u63a5\u6284\u7684\u5b8c\u6574\u4ee3\u7801\uff0c\u5efa\u8bae\u5148\u6536\u85cf\u3002<\/p>\n\n\n\n

\u00b7 \u00b7 \u00b7<\/p>\n\n\n\n

\u4e00\u3001\u6211\u60f3\u9a8c\u8bc1\u4e00\u4ef6\u4e8b<\/strong><\/h2>\n\n\n\n

\u6280\u672f\u6307\u6807\u5230\u5e95\u8fd8\u6709\u6ca1\u6709\u7528\uff1f<\/p>\n\n\n\n

\u5747\u7ebf\u3001RSI\u3001\u91cf\u6bd4\u3001\u6ce2\u52a8\u7387\u88ab\u5199\u4e86\u4e09\u5341\u5e74\uff0c\u6bcf\u672c\u5165\u95e8\u4e66\u90fd\u5728\u6559\u3002\u53ef\u6211\u6309\u5b83\u4eec\u505a\u7684\u65f6\u5019\uff0c\u7ed3\u679c\u603b\u5dee\u4e0d\u591a\uff0c\u6709\u65f6\u5019\u5bf9\uff0c\u6709\u65f6\u5019\u9519\uff0c\u62c9\u957f\u770b\u8ddf\u6ca1\u505a\u4e00\u6837\u3002\u9ebb\u70e6\u5728\u4e8e\u4eba\u5de5\u6837\u672c\u592a\u5c0f\uff0c\u51e0\u5341\u7b14\u4ea4\u6613\u8bf4\u660e\u4e0d\u4e86\u4ec0\u4e48\uff0c\u4eba\u53c8\u53ea\u8bb0\u5f97\u8499\u5bf9\u7684\u90a3\u51e0\u6b21\u3002<\/p>\n\n\n\n

\u6240\u4ee5\u6211\u6362\u4e86\u4e2a\u95ee\u6cd5\u300211 \u4e2a\u6700\u5e38\u89c1\u7684\u6307\u6807\u5168\u5582\u7ed9\u6a21\u578b\uff0c\u8ba9\u5b83\u81ea\u5df1\u7ec4\u5408\u3001\u81ea\u5df1\u6743\u8861\uff0c\u518d\u628a 17 \u5e74\u534a\u30014412 \u4e2a\u4ea4\u6613\u65e5\u8dd1\u4e00\u904d\u3002\u5982\u679c\u8fd9\u6837\u90fd\u627e\u4e0d\u5230\u65b9\u5411\uff0c\u90a3\u95ee\u9898\u5c31\u4e0d\u5728\u6307\u6807\u600e\u4e48\u7528\uff0c\u800c\u5728\u660e\u5929\u5f80\u54ea\u8d70\u672c\u8eab\u3002<\/p>\n\n\n\n

\u505a\u591a\u65e5\u7684\u65b9\u5411\u51c6\u786e\u7387 55.35%\u3002\u629b\u786c\u5e01\u662f 50%\uff0c\u9ad8\u51fa\u4e94\u4e2a\u591a\u70b9\uff0c\u662f\u4e2a\u80fd\u62ff\u53bb\u89c1\u4eba\u7684\u6570\u5b57\u3002\u4f46\u6211\u62c6\u5f00\u770b\u4e86\u4e00\u904d\uff0c\u7ad9\u4e0d\u4f4f\uff0c17 \u5e74\u534a\u4e0b\u6765\uff0c\u5b83\u7684\u603b\u6536\u76ca\u53ea\u6709\u4e00\u76f4\u6301\u6709 SPY \u7684\u4e00\u534a\u3002<\/p>\n\n\n\n

\"\"
11 \u4e2a\u6280\u672f\u6307\u6807\u4ea4\u7ed9\u6a21\u578b\uff0c\u8ba9\u5b83\u81ea\u5df1\u51b3\u5b9a\u660e\u5929\u6da8\u8fd8\u662f\u8dcc<\/figcaption><\/figure>\n\n\n\n

\u8fd9\u662f\u4e00\u7bc7\u8bb2\u201c\u5931\u8d25\u201d\u7684\u6587\u7ae0\u3002\u4f46\u6bd4\u201c\u5931\u8d25\u201d\u66f4\u503c\u5f97\u8bf4\u7684\u5728\u540e\u9762\u3002<\/p>\n\n\n\n

\u4e8c\u3001\u6a21\u578b\u957f\u4ec0\u4e48\u6837<\/strong><\/h2>\n\n\n\n

\u5b83\u53ea\u56de\u7b54\u4e00\u4e2a\u95ee\u9898\uff0c\u660e\u5929\u6536\u76d8\u4ef7\u6bd4\u4eca\u5929\u9ad8\u5417\u3002\u7b54\u6848\u53ea\u6709\u4e24\u4e2a\uff0c\u6da8\u6216\u8005\u8dcc\u3002<\/p>\n\n\n\n

\u5582\u8fdb\u53bb\u7684 11 \u4e2a\u7279\u5f81\u5168\u4ece\u4ef7\u683c\u548c\u6210\u4ea4\u91cf\u7b97\u51fa\u6765\u3002\u56db\u4e2a\u5468\u671f\u7684\u52a8\u91cf\u3001RSI\u300110 \u65e5\u7ebf\u6bd4 50 \u65e5\u7ebf\u3001\u4e24\u4e2a\u6ce2\u52a8\u7387\u3001\u4e24\u4e2a\u91cf\u80fd\uff0c\u6700\u540e\u4e00\u4e2a\u662f\u661f\u671f\u51e0\u3002<\/p>\n\n\n\n

\u8d85\u53c2\u6570\u8bbe\u5f97\u5f88\u4fdd\u5b88\u3002\u6811\u53ea\u957f\u5230 4 \u5c42\uff0c\u6bcf\u5c42\u6700\u591a 15 \u4e2a\u53f6\u5b50\uff0c\u884c\u548c\u5217\u5404\u505a 80% \u91c7\u6837\u3002\u65e5\u7ebf\u6536\u76ca\u7684\u4fe1\u566a\u6bd4\u51fa\u4e86\u540d\u5730\u5dee\uff0c\u914d\u7f6e\u4e00\u6fc0\u8fdb\uff0c\u6a21\u578b\u5c31\u4f1a\u628a\u8bad\u7ec3\u7a97\u91cc\u7684\u566a\u97f3\u80cc\u4e0b\u6765\u3002<\/p>\n\n\n\n

\u4ea4\u6613\u89c4\u5219\u66f4\u7b80\u5355\uff0c\u7b97\u51fa\u7684\u4e0a\u6da8\u6982\u7387\u8d85\u8fc7 53% \u5c31\u6301\u6709\uff0c\u5426\u5219\u62ff\u73b0\u91d1\u3002<\/p>\n\n\n\n

\u8bad\u7ec3\u65b9\u5f0f\u5361\u5f97\u6700\u4e25\uff0c\u8d70\u524d\u5411\u9a8c\u8bc1\u3002\u53ea\u7528\u5f53\u524d\u65f6\u95f4\u70b9\u524d\u7684\u6570\u636e\u8bad\u7ec3\uff0c\u6bcf63\u4e2a\u4ea4\u6613\u65e5\u91cd\u65b0\u62df\u5408\u4e00\u6b21\uff0c\u518d\u62ff63\u5929\u505a\u6d4b\u8bd5\uff0c\u6a21\u578b\u6c38\u8fdc\u770b\u4e0d\u5230\u5b83\u8981\u5224\u65ad\u7684\u90a3\u4e00\u5929\u3002<\/p>\n\n\n\n

\u8fd9\u662f\u57fa\u672c\u529f\uff0c\u4f46\u5e02\u9762\u4e0a\u5927\u90e8\u5206AI\u4ea4\u6613\u673a\u5668\u4eba\u7684\u6f14\u793a\u4e0d\u4f1a\u505a\uff0c\u5b83\u4eec\u7ed9\u4f60\u770b\u7684\u66f2\u7ebf\u662f\u6a21\u578b\u5728\u89c1\u8fc7\u7b54\u6848\u7684\u6570\u636e\u4e0a\u8dd1\u51fa\u6765\u7684\u3002<\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

\u8d70\u524d\u5411\u9a8c\u8bc1\u3002\u8bad\u7ec3\u7a97\u6574\u4f53\u5f80\u524d\u63a8\uff0c\u6d4b\u8bd5\u6bb5\u6c38\u8fdc\u8ddf\u5728\u540e\u9762\uff0c\u6a21\u578b\u78b0\u4e0d\u5230\u672a\u6765\u7684\u6570\u636e<\/p>\n\n\n\n

\u4e09\u300155.35% \u8fd9\u4e2a\u6570\uff0c\u7ecf\u4e0d\u8d77\u62c6<\/strong><\/h2>\n\n\n\n

\u6570\u636e\u53d6 SPY \u65e5\u7ebf\uff0c\u672a\u590d\u6743\uff0c6414 \u6839\u3002\u8bc4\u4f30\u533a\u95f4 2009-03-02 \u5230 2026-09-15\uff0c4412 \u4e2a\u4ea4\u6613\u65e5\u3002<\/p>\n\n\n\n

\u6307\u6807<\/th>\u672c\u6587\u5b9e\u6d4b<\/th><\/tr>
\u505a\u591a\u65e5\u65b9\u5411\u51c6\u786e\u7387<\/td>55.35%<\/td><\/tr>
\u5728\u573a\u65f6\u95f4\u5360\u6bd4<\/td>59.5%<\/td><\/tr>
\u5e74\u5316\u6536\u76ca<\/td>10.27%<\/td><\/tr>
\u6700\u5927\u56de\u64a4<\/td>\u221230.94%<\/td><\/tr>
\u590f\u666e<\/td>0.76<\/td><\/tr>
\u533a\u95f4\u603b\u6536\u76ca<\/td>+453.98%<\/td><\/tr>
\u540c\u671f\u4e00\u76f4\u6301\u6709 SPY<\/td>+968.06%<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n

\u5148\u770b\u597d\u7684\u4e00\u9762\u300259.5% \u7684\u65f6\u95f4\u5728\u573a\uff0c\u56de\u64a4\u221230.94%\uff0c\u6bd4\u4e00\u76f4\u6301\u6709\u7684\u221234.10% \u6d45\u4e863.16\u4e2a\u767e\u5206\u70b9\u3002\u4f46\u8d26\u653e\u4e00\u8d77\u7b97\u5c31\u4e0d\u5bf9\uff0c\u5e74\u5316\u6bd4\u4e00\u76f4\u6301\u6709\u4f4e4.22\u4e2a\u767e\u5206\u70b9\u3002<\/p>\n\n\n\n

\u771f\u6b63\u5173\u952e\u7684\u662f\u4e0b\u4e00\u4e2a\u95ee\u9898\u3002SPY \u81ea\u5df1\u4ec0\u4e48\u90fd\u4e0d\u505a\uff0c\u4e0a\u6da8\u7684\u65e5\u5b50\u5360\u591a\u5c11\u3002<\/p>\n\n\n\n

\u6211\u6309\u4e24\u4e2a\u53e3\u5f84\u7b97\u4e86\u4e00\u904d\u3002\u4eca\u5929\u6536\u76d8\u6bd4\u6628\u5929\u6536\u76d8\u9ad8\uff0c\u662f 54.99%\uff1b\u6bd4\u4eca\u5929\u5f00\u76d8\u9ad8\uff0c\u662f 54.47%\u3002\u6a21\u578b\u7684 55.35%\uff0c\u6bd4\u7b2c\u4e00\u4e2a\u9ad8 0.37 \u4e2a\u767e\u5206\u70b9\uff0c\u6bd4\u7b2c\u4e8c\u4e2a\u9ad8 0.89 \u4e2a\u767e\u5206\u70b9\u3002<\/p>\n\n\n\n

0.37 \u4e2a\u767e\u5206\u70b9\u662f\u4ec0\u4e48\u6982\u5ff5\u30022625 \u4e2a\u505a\u591a\u65e5\uff0c\u8fd9\u4e2a\u6837\u672c\u91cf\u4e0b\u6807\u51c6\u8bef\u7ea6 0.97 \u4e2a\u767e\u5206\u70b9\uff0c0.37 \u8fd8\u4e0d\u5230\u534a\u4e2a\u6807\u51c6\u5dee\uff0cp \u503c\u5728 0.7 \u9644\u8fd1\uff0c\u6362\u4e2a\u968f\u673a\u79cd\u5b50\u5c31\u80fd\u76d6\u8fc7\u53bb\u3002<\/p>\n\n\n\n

\u7edf\u8ba1\u4e0a\u8fd9\u53eb\u4e0d\u663e\u8457\uff0c\u4f60\u6ca1\u6cd5\u628a\u5b83\u548c\u4ec0\u4e48\u90fd\u6ca1\u6709\u533a\u5206\u5f00\u3002<\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

\u5b9e\u6d4b\u7ed3\u679c\u3002\u7d2b\u7ebf\u662f\u6a21\u578b\u62e9\u65f6\uff0c\u7070\u7ebf\u662f\u4e00\u76f4\u6301\u6709 SPY\u3002\u6a21\u578b\u51c0\u503c 5.54 \u500d\uff0c\u4e00\u76f4\u6301\u6709 10.68 \u500d<\/p>\n\n\n\n

\u56db\u3001\u80fd\u4e00\u9524\u5b9a\u97f3\u7684\u662f\u6821\u51c6<\/strong><\/h2>\n\n\n\n

\u90a3\u600e\u4e48\u5206\u6e05\u4e00\u4e2a\u6a21\u578b\u662f\u771f\u6709\u4fe1\u53f7\uff0c\u8fd8\u662f\u7eaf\u8e6d\u57fa\u51c6\u7387\u3002<\/p>\n\n\n\n

\u6709\u4e2a\u5f88\u5e72\u51c0\u7684\u68c0\u9a8c\uff0c\u53eb\u6821\u51c6\u3002\u5982\u679c\u6a21\u578b\u771f\u6709\u5224\u65ad\u529b\uff0c\u5b83\u8d8a\u6709\u628a\u63e1\u7684\u65f6\u5019\u5c31\u8be5\u8d8a\u51c6\u3002<\/p>\n\n\n\n

\u6211\u628a\u8bc4\u4f30\u671f\u6bcf\u4e00\u5929\u7684\u8f93\u51fa\u6982\u7387\u62ff\u51fa\u6765\uff0c\u6309\u95e8\u69db\u4ece 50% \u63d0\u5230 68%\uff0c\u770b\u95e8\u69db\u4ee5\u4e0a\u90a3\u6279\u65e5\u5b50\u7684\u5b9e\u9645\u6b63\u786e\u7387\u3002<\/p>\n\n\n\n

\u7ed3\u679c\u662f\u4e00\u6761\u6a2a\u7ebf\u3002\u95e8\u69db 50% \u65f6\u6b63\u786e\u7387 55.06%\uff0c53% \u65f6 55.35%\uff0c\u518d\u5f80\u4e0a\u8d70\u5f00\u59cb\u6389\uff0c65% \u53ea\u5269 54.18%\uff0c68% \u662f 53.95%\u3002<\/p>\n\n\n\n

\u771f\u6709\u4fe1\u53f7\u7684\u6a21\u578b\uff0c\u8fd9\u6761\u7ebf\u8be5\u5f80\u4e0a\u8d70\u3002\u8fd9\u91cc\u662f\u4e00\u6761\u5e73\u7684\u7ebf\uff0c\u6700\u9ad8\u7f6e\u4fe1\u7684\u90a3\u6279\u65e5\u5b50\u751a\u81f3\u66f4\u5dee\u3002<\/p>\n\n\n\n

\u4e3a\u4ec0\u4e48\uff0c\u770b\u6982\u7387\u5206\u5e03\u5c31\u660e\u767d\u3002\u6a21\u578b\u7ed9\u51fa\u7684\u4e0a\u6da8\u6982\u7387\u5168\u5806\u5728 0.5 \u9644\u8fd1\uff0c\u5747\u503c 0.5478\uff0c\u6807\u51c6\u5dee\u53ea\u6709 0.108\uff0c31.4% \u7684\u65e5\u5b50\u843d\u5728 0.45 \u5230 0.55 \u4e4b\u95f4\u3002\u5b83\u65e2\u4e0d\u662f\u5f88\u6709\u628a\u63e1\u5730\u5bf9\uff0c\u4e5f\u4e0d\u662f\u5f88\u6709\u628a\u63e1\u5730\u9519\uff0c\u5c31\u662f\u4e0d\u77e5\u9053\u3002<\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

\u6821\u51c6\u66f2\u7ebf\u3002\u6a2a\u8f74\u662f\u95e8\u69db\uff0c\u7eb5\u8f74\u662f\u5b9e\u9645\u6b63\u786e\u7387\uff0c\u7ea2\u7ebf\u662f 54.99% \u7684\u57fa\u51c6\u7387\u3002\u6574\u6761\u7ebf\u7ed5\u7740\u5b83\u4e0a\u4e0b\u6446<\/p>\n\n\n\n

\u4e94\u3001\u6211\u53c8\u8865\u4e86\u51e0\u7ec4\u5bf9\u7167<\/strong><\/h2>\n\n\n\n

\u7ed3\u8bba\u5230\u8fd9\u91cc\u5df2\u7ecf\u6e05\u695a\u3002\u4e3a\u4e86\u5835\u6b7b\u6570\u636e\u6ca1\u9009\u597d\u8fd9\u6761\u8def\uff0c\u6211\u53c8\u52a0\u4e86\u51e0\u7ec4\u3002<\/p>\n\n\n\n

\u7b2c\u4e00\u7ec4\uff0c\u628a\u7b54\u6848\u6253\u4e71\u3002<\/strong> \u8bad\u7ec3\u4e4b\u524d\uff0c\u6211\u628a\u76ee\u6807\u5217\u6574\u5217\u968f\u673a\u6d17\u724c\uff0c\u8dd1\u5b8c\u5168\u76f8\u540c\u7684\u6d41\u7a0b\uff0c\u6a21\u578b\u624b\u4e0a\u6ca1\u6709\u4efb\u4f55\u53ef\u5b66\u4fe1\u606f\u3002\u8dd1\u4e09\u904d\uff0c\u505a\u591a\u65e5\u7684\u51c6\u786e\u7387\u5206\u522b\u662f 55.15%\u300154.78%\u300154.25%\uff0c\u5e73\u5747 54.73%\uff0c\u771f\u6a21\u578b 55.35%\uff0c\u5dee 0.62 \u4e2a\u767e\u5206\u70b9\u3002\u8fd9\u8bf4\u660e 55% \u8fd9\u4e2a\u91cf\u7ea7\u6839\u672c\u4e0d\u6765\u81ea\u6a21\u578b\u3002\u6807\u666e\u8fd9 17 \u5e74\u672c\u6765\u5c31\u662f\u6da8\u7684\u65e5\u5b50\u591a\uff0c\u6a21\u578b\u53ea\u8981\u591a\u6570\u65f6\u5019\u8bf4\u6da8\uff0c\u5c31\u80fd\u62ff\u5230\u8fd9\u4e2a\u5206\u6570\u3002<\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

\u5de6\u8fb9\u662f\u6a21\u578b\uff0c\u4e2d\u95f4\u662f\u6362\u79cd\u5b50\u548c\u6253\u4e71\u6807\u7b7e\uff0c\u53f3\u8fb9\u662f\u57fa\u51c6\u7387\u3002\u5168\u90e8\u6324\u5728 54.5% \u5230 55.6% \u4e4b\u95f4<\/p>\n\n\n\n

\u7b2c\u4e8c\u7ec4\uff0c\u628a\u8fdb\u51fa\u573a\u7684\u65e5\u5b50\u6362\u6210\u968f\u673a\u3002<\/strong> \u628a\u4fe1\u53f7\u6362\u6210\u968f\u673a\u6570\uff0c\u4fdd\u6301\u540c\u6837\u7684 59.5% \u5728\u573a\u6bd4\u4f8b\u8dd1 200 \u6b21\u3002\u533a\u95f4\u603b\u6536\u76ca\u4e2d\u4f4d\u6570 +302.85%\uff0c\u6a21\u578b\u6392\u5728 84 \u5206\u4f4d\uff1b\u6700\u5927\u56de\u64a4\u4e2d\u4f4d\u6570 \u221228.14%\uff0c\u6bd4\u6a21\u578b\u7684 \u221230.94% \u8fd8\u6d45\u3002\u7b2c\u4e09\u8282\u90a3 3.16 \u4e2a\u767e\u5206\u70b9\u7684\u56de\u64a4\u6539\u5584\uff0c\u5230\u8fd9\u91cc\u89e3\u91ca\u6e05\u695a\u4e86\uff0c\u5b83\u6765\u81ea\u4ed3\u4f4d\u964d\u4f4e\uff0c\u4e0d\u662f\u5224\u65ad\u529b\u3002<\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

\u968f\u673a\u8fdb\u51fa\u573a\u8dd1 200 \u6b21\uff0c\u84dd\u7ebf\u662f\u6a21\u578b\u7684\u4f4d\u7f6e<\/p>\n\n\n\n

\u8fd8\u6709\u4e09\u7ec4\u3002<\/strong> \u53ea\u6539\u968f\u673a\u79cd\u5b50\u8dd1\u4e94\u904d\uff0c\u533a\u95f4\u603b\u6536\u76ca\u4ece +200.90% \u62c9\u5230 +453.98%\uff0c\u8de8\u5ea6 253 \u4e2a\u767e\u5206\u70b9\u3002\u6574\u6bb5\u6570\u636e\u4e00\u6b21\u5582\u8fdb\u53bb\uff0c\u6a21\u578b\u5728\u540c\u4e00\u6837\u672c\u4e0a\u5224\u65ad\u80fd\u5230 63.17%\uff0c\u6bd4\u6837\u672c\u5916\u9ad8 7.82 \u4e2a\u767e\u5206\u70b9\u3002\u52a0\u4e0a\u6bcf\u5e74 89.7 \u6b21\u6362\u624b\u548c 0.02% \u6210\u672c\uff0c\u603b\u6536\u76ca\u6389\u5230 +304.72%\u3002\u597d\u770b\u7684\u90a3\u90e8\u5206\u90fd\u662f\u5047\u7684\u3002<\/p>\n\n\n\n

\u516d\u3001\u52a8\u624b\u533a\uff0c\u628a\u6821\u51c6\u68c0\u67e5\u5199\u6210\u4ee3\u7801<\/strong><\/h2>\n\n\n\n

\u4ee5\u4e0a\u662f\u7ed3\u8bba\u3002\u4e0b\u9762\u662f\u80fd\u76f4\u63a5\u7167\u505a\u7684\u5b9e\u73b0\uff0c\u56db\u4e2a\u51fd\u6570\u3002<\/p>\n\n\n\n

\u7b2c\u4e00\u6b65\uff0c\u9020 11 \u4e2a\u7279\u5f81\u3002<\/p>\n\n\n\n

FEATURE_COLS = [\n    'ret1', 'ret5', 'ret10', 'ret20', 'rsi14', 'ma_ratio',\n    'atr_pct', 'vol20', 'vol_change', 'vol_ratio', 'dow',\n]\n\n\ndef build_features(df):\n    df['ret1'] = df['Close'].pct_change(1)\n    df['ret5'] = df['Close'].pct_change(5)\n    df['ret10'] = df['Close'].pct_change(10)\n    df['ret20'] = df['Close'].pct_change(20)\n\n    delta = df['Close'].diff()\n    gain = delta.clip(lower=0)\n    loss = -delta.clip(upper=0)\n    avg_gain = gain.ewm(alpha=1 \/ 14, min_periods=14).mean()\n    avg_loss = loss.ewm(alpha=1 \/ 14, min_periods=14).mean()\n    df['rsi14'] = 100 - (100 \/ (1 + avg_gain \/ avg_loss))\n\n    df['ma_ratio'] = df['Close'].rolling(10).mean() \/ df['Close'].rolling(50).mean() - 1\n\n    tr = pd.concat([\n        df['High'] - df['Low'],\n        (df['High'] - df['Close'].shift()).abs(),\n        (df['Low'] - df['Close'].shift()).abs(),\n    ], axis=1).max(axis=1)\n    df['atr_pct'] = tr.rolling(14).mean() \/ df['Close']\n\n    df['vol20'] = df['ret1'].rolling(20).std() * np.sqrt(252)\n    df['vol_change'] = df['Volume'].pct_change(5)\n    df['vol_ratio'] = df['Volume'] \/ df['Volume'].rolling(20).mean()\n    df['dow'] = df.index.dayofweek\n\n    df['target'] = (df['Close'].shift(-1) > df['Close']).astype(int)\n    df['fwd_ret'] = df['Close'].shift(-1) \/ df['Close'] - 1\n    return df<\/code><\/pre>\n\n\n\n
\u7b2c\u4e8c\u6b65\uff0c\u8d70\u524d\u5411\u9a8c\u8bc1\u8dd1\u51fa\u6982\u7387\u3002 \u8fd9\u6bb5\u662f\u5168\u6587\u6700\u91cd\u8981\u7684\u4ee3\u7801\uff0c\u6ce8\u610f `train` \u6c38\u8fdc\u53ea\u53d6 `i` \u4e4b\u524d\u7684\u884c\u3002<\/p>\n\n\n\n
def walk_forward(df, train_window=1000, refit_every=63, seed=42):\n    prob = np.full(len(df), np.nan)\n    i = train_window\n\n    while i < len(df):\n        train = df.iloc[i - train_window:i]\n        model = lgb.LGBMClassifier(\n            n_estimators=100,\n            max_depth=4,\n            learning_rate=0.05,\n            num_leaves=15,\n            min_child_samples=30,\n            subsample=0.8,\n            colsample_bytree=0.8,\n            random_state=seed,\n            verbose=-1,\n        )\n        model.fit(train[FEATURE_COLS], train['target'])\n\n        end = min(i + refit_every, len(df))\n        prob[i:end] = model.predict_proba(df.iloc[i:end][FEATURE_COLS])[:, 1]\n        i = end\n\n    return prob<\/code><\/pre>\n\n\n\n
\u7b2c\u4e09\u6b65\uff0c\u6821\u51c6\u68c0\u67e5\u3002 \u597d\u6a21\u578b\u7684\u7cbe\u5ea6\u8be5\u968f\u95e8\u69db\u62ac\u9ad8\u800c\u660e\u663e\u4e0a\u5347\uff0c\u8dd1\u51fa\u6765\u662f\u5e73\u7684\uff0c\u540e\u9762\u7684\u7ee9\u6548\u8868\u5c31\u4e0d\u7528\u770b\u4e86\u3002<\/p>\n\n\n\n
def calibration_check(df, thresholds=np.arange(0.50, 0.681, 0.01)):\n    base_rate = df['target'].mean()          # \u65e0\u6761\u4ef6\u57fa\u51c6\u7387\n    print(f\"\u57fa\u51c6\u7387 {base_rate:.2%}\")\n\n    for th in thresholds:\n        sub = df[df['pred_prob'] > th]\n        if len(sub) < 20:\n            continue\n        print(f\"\u95e8\u69db {th:.2f}  \u6837\u672c {len(sub):5d}  \u7cbe\u5ea6 {sub['target'].mean():.2%}\")<\/code><\/pre>\n\n\n\n
\u7b2c\u56db\u6b65\uff0c\u6253\u4e71\u6807\u7b7e\u3002 \u8fd9\u4e00\u6b65\u4e89\u8bae\u6700\u5c11\uff0c\u4e5f\u6700\u80fd\u8bf4\u670d\u4eba\u3002\u8dd1\u4e09\u6b21\u5982\u679c\u548c\u771f\u6a21\u578b\u7684\u6570\u5b57\u5dee\u4e0d\u591a\uff0c\u8bf4\u660e\u4f60\u90a3\u4e2a\u51c6\u786e\u7387\u8ddf\u6a21\u578b\u7684\u80fd\u529b\u6ca1\u5173\u7cfb\u3002<\/p>\n\n\n\n
def shuffled_label_test(df, n_runs=3):\n    for k in range(n_runs):\n        y = np.random.default_rng(k).permutation(df['target'].values)\n        prob = walk_forward_with_y(df, y)\n        sub = df[prob > 0.53]\n        print(f\"\u7b2c {k + 1} \u6b21  \u505a\u591a\u65e5\u51c6\u786e\u7387 {sub['target'].mean():.2%}\")<\/code><\/pre>\n\n\n\n
\u7b2c\u4e94\u6b65\uff0c\u5b8c\u6574\u811a\u672c\uff0c\u590d\u5236\u5c31\u80fd\u8dd1\u3002 \u524d\u9762\u56db\u6bb5\u62fc\u8d77\u6765\u5c31\u662f\u5b8c\u6574\u5b9e\u73b0\uff0c\u7b2c\u4e8c\u6b21\u8fd0\u884c\u4e0d\u518d\u8054\u7f51\u3002<\/p>\n\n\n\n
# -*- coding: utf-8 -*-\n\n\"\"\"\nLightGBM \u65e5\u7ebf\u65b9\u5411\u6a21\u578b\uff0c\u5b8c\u6574\u53ef\u8fd0\u884c\u7248\u672c\u3002\n\u6570\u636e\u6e90  akshare \u65b0\u6d6a\u7f8e\u80a1 SPY \u65e5\u7ebf\uff08\u672a\u590d\u6743\uff0c\u9996\u6b21\u8fd0\u884c\u4f1a\u8054\u7f51\u4e0b\u8f7d\u5e76\u7f13\u5b58\uff09\n\u6d41\u7a0b    11 \u4e2a\u6280\u672f\u7279\u5f81 -> walk-forward \u6eda\u52a8\u8bad\u7ec3 -> \u6982\u7387\u95e8\u69db\u62e9\u65f6 -> \u6821\u51c6\u68c0\u67e5 -> \u6210\u672c\u654f\u611f\u6027\n\u8f93\u51fa    \u7ee9\u6548\u5bf9\u7167\u8868\u3001\u6821\u51c6\u66f2\u7ebf\u6570\u636e\u3001\u7279\u5f81\u91cd\u8981\u6027\n\"\"\"\n\nimport os\n\nimport numpy as np\nimport pandas as pd\nimport akshare as ak\nfrom lightgbm import LGBMClassifier\n\nFEATURE_COLS = [\n    'ret1', 'ret5', 'ret10', 'ret20', 'rsi14', 'ma_ratio',\n    'atr_pct', 'vol20', 'vol_change', 'vol_ratio', 'dow',\n]\n\nTRAIN_WINDOW = 1000     # \u7528\u8fc7\u53bb\u7ea6 4 \u5e74\u7684\u65e5\u7ebf\u505a\u8bad\u7ec3\nREFIT_EVERY = 63        # \u6bcf 63 \u4e2a\u4ea4\u6613\u65e5\u91cd\u65b0\u62df\u5408\u4e00\u6b21\nPROB_THRESHOLD = 0.53   # \u6982\u7387\u8d85\u8fc7 53% \u624d\u6301\u6709\uff0c\u5426\u5219\u7a7a\u4ed3\nEVAL_START = '2009-03-01'\nCACHE = 'spy_daily_cache.csv'\n\n\ndef load_data():\n    \"\"\"\u53d6 SPY \u65e5\u7ebf\u3002\u7b2c\u4e00\u6b21\u8054\u7f51\u4e0b\u8f7d\uff0c\u4e4b\u540e\u8d70\u672c\u5730\u7f13\u5b58\u3002\"\"\"\n    if os.path.exists(CACHE):\n        df = pd.read_csv(CACHE, parse_dates=['date'])\n    else:\n        df = ak.stock_us_daily(symbol='SPY')\n        df['date'] = pd.to_datetime(df['date'])\n        df.to_csv(CACHE, index=False)\n\n    df = df.rename(columns={\n        'open': 'Open', 'high': 'High',\n        'low': 'Low', 'close': 'Close', 'volume': 'Volume',\n    })\n    return df.set_index('date').sort_index()\n\n\ndef build_features(df):\n    \"\"\"\u628a\u539f\u59cb OHLCV \u53d8\u6210 11 \u4e2a\u7279\u5f81\uff0c\u5916\u52a0\u76ee\u6807\u5217\u548c\u6b21\u65e5\u6536\u76ca\u3002\"\"\"\n    df = df.copy()\n    df['ret1'] = df['Close'].pct_change(1)\n    df['ret5'] = df['Close'].pct_change(5)\n    df['ret10'] = df['Close'].pct_change(10)\n    df['ret20'] = df['Close'].pct_change(20)\n\n    delta = df['Close'].diff()\n    gain = delta.clip(lower=0)\n    loss = -delta.clip(upper=0)\n    avg_gain = gain.ewm(alpha=1 \/ 14, min_periods=14).mean()\n    avg_loss = loss.ewm(alpha=1 \/ 14, min_periods=14).mean()\n    df['rsi14'] = 100 - (100 \/ (1 + avg_gain \/ avg_loss))\n\n    df['ma_ratio'] = df['Close'].rolling(10).mean() \/ df['Close'].rolling(50).mean() - 1\n\n    tr = pd.concat([\n        df['High'] - df['Low'],\n        (df['High'] - df['Close'].shift()).abs(),\n        (df['Low'] - df['Close'].shift()).abs(),\n    ], axis=1).max(axis=1)\n    df['atr_pct'] = tr.rolling(14).mean() \/ df['Close']\n\n    df['vol20'] = df['ret1'].rolling(20).std() * np.sqrt(252)\n    df['vol_change'] = df['Volume'].pct_change(5)\n    df['vol_ratio'] = df['Volume'] \/ df['Volume'].rolling(20).mean()\n    df['dow'] = df.index.dayofweek\n\n    df['target'] = (df['Close'].shift(-1) > df['Close']).astype(int)\n    df['fwd_ret'] = df['Close'].shift(-1) \/ df['Close'] - 1\n    return df.dropna(subset=FEATURE_COLS + ['target'])\n\n\ndef walk_forward(df, seed=42, train_window=TRAIN_WINDOW, refit_every=REFIT_EVERY):\n    \"\"\"\u6eda\u52a8\u8bad\u7ec3\u5e76\u8f93\u51fa\u6bcf\u4e00\u5929\u7684\u4e0a\u6da8\u6982\u7387\u3002\u8bad\u7ec3\u96c6\u6c38\u8fdc\u53ea\u7528\u5f53\u5929\u4e4b\u524d\u7684\u6570\u636e\u3002\"\"\"\n    prob = np.full(len(df), np.nan)\n    importances = []\n    i = train_window\n\n    while i < len(df):\n        train = df.iloc[i - train_window:i]\n        model = LGBMClassifier(\n            n_estimators=100, max_depth=4, learning_rate=0.05,\n            num_leaves=15, min_child_samples=30,\n            subsample=0.8, colsample_bytree=0.8,\n            random_state=seed, verbose=-1,\n        )\n        model.fit(train[FEATURE_COLS], train['target'])\n\n        end = min(i + refit_every, len(df))\n        prob[i:end] = model.predict_proba(df.iloc[i:end][FEATURE_COLS])[:, 1]\n        importances.append(pd.Series(model.feature_importances_, index=FEATURE_COLS))\n        i = end\n\n    return prob, importances\n\n\ndef stats(ret):\n    \"\"\"\u628a\u65e5\u6536\u76ca\u5e8f\u5217\u6362\u7b97\u6210\u5e74\u5316\u3001\u56de\u64a4\u3001\u590f\u666e\u3002\"\"\"\n    ret = ret.dropna()\n    nav = (1 + ret).cumprod()\n    years = len(ret) \/ 252\n    cagr = nav.iloc[-1] ** (1 \/ years) - 1\n    mdd = (nav \/ nav.cummax() - 1).min()\n    sharpe = ret.mean() \/ ret.std() * np.sqrt(252)\n    return dict(\n        \u603b\u6536\u76ca=f\"{nav.iloc[-1] - 1:.2%}\",\n        \u5e74\u5316=f\"{cagr:.2%}\",\n        \u6700\u5927\u56de\u64a4=f\"{mdd:.2%}\",\n        \u590f\u666e=f\"{sharpe:.2f}\",\n    )\n\n\ndef main():\n    df = build_features(load_data())\n    start = max(int(df.index.searchsorted(pd.Timestamp(EVAL_START))), TRAIN_WINDOW)\n    prob, imps = walk_forward(df, seed=42)\n\n    ev = df.iloc[start:].copy()\n    ev['prob'] = prob[start:]\n    ev = ev.dropna(subset=['prob', 'fwd_ret'])\n    ev['signal'] = (ev['prob'] > PROB_THRESHOLD).astype(int)\n    print(f\"\u6837\u672c {ev.index[0].date()} ~ {ev.index[-1].date()}\uff0c{len(ev)} \u4e2a\u4ea4\u6613\u65e5\")\n\n    # 1 \u57fa\u51c6\u7387\u4e0e\u51c6\u786e\u7387\n    base = ev['target'].mean()\n    acc = ev.loc[ev['signal'] == 1, 'target'].mean()\n    print(f\"\\n\u65e0\u6761\u4ef6\u4e0a\u6da8\u65e5\u5360\u6bd4 {base:.2%}\")\n    print(f\"\u6a21\u578b\u505a\u591a\u65e5\u51c6\u786e\u7387 {acc:.2%}\uff0c\u8d85\u989d {(acc - base) * 100:.2f} \u4e2a\u767e\u5206\u70b9\")\n    print(f\"\u5728\u573a\u65f6\u95f4\u5360\u6bd4 {ev['signal'].mean():.1%}\")\n\n    # 2 \u7ee9\u6548\u5bf9\u7167\n    print(\"\\n\u6a21\u578b\u62e9\u65f6\", stats(ev['signal'] * ev['fwd_ret']))\n    print(\"\u4e00\u76f4\u6301\u6709\", stats(ev['fwd_ret']))\n\n    # 3 \u6821\u51c6\u68c0\u67e5\uff0c\u8fd9\u4e00\u6b65\u51b3\u5b9a\u8981\u4e0d\u8981\u7ee7\u7eed\u770b\u4e0b\u53bb\n    print(\"\\n\u95e8\u69db   \u6837\u672c   \u7cbe\u5ea6\")\n    for th in np.arange(0.50, 0.681, 0.01):\n        sub = ev[ev['prob'] > th]\n        if len(sub) >= 20:\n            print(f\"{th:.2f}  {len(sub):5d}  {sub['target'].mean():.2%}\")\n\n    # 4 \u7279\u5f81\u91cd\u8981\u6027\n    imp = pd.concat(imps, axis=1).mean(axis=1).sort_values(ascending=False)\n    print(\"\\n\u7279\u5f81\u91cd\u8981\u6027\uff08\u5b63\u5ea6\u91cd\u8bad\u5747\u503c\uff09\")\n    print(imp.round(1).to_string())\n\n    # 5 \u6210\u672c\u654f\u611f\u6027\uff0c\u6bcf\u5e74\u6362\u624b\u7ea6 89 \u6b21\n    turn = ev['signal'].diff().abs().fillna(0)\n    print(f\"\\n\u6bcf\u5e74\u6362\u624b {turn.sum() \/ (len(ev) \/ 252):.1f} \u6b21\")\n    for cost in [0, 0.0001, 0.0002, 0.0005]:\n        print(f\"\u5355\u8fb9\u6210\u672c {cost:.2%}\", stats(ev['signal'] * ev['fwd_ret'] - turn * cost))\n\n\nif __name__ == '__main__':\n    main()<\/code><\/pre>\n\n\n\n
\u4e03\u3001\u5230\u5e95\u5b66\u5230\u4e86\u4ec0\u4e48<\/strong><\/h2>\n\n\n\n
\u6709\u4e00\u70b9\u5f97\u8bf4\u6e05\uff0c\u6a21\u578b\u4e0d\u662f\u5728\u4e71\u6765\u3002<\/p>\n\n\n\n
\u6211\u628a 71 \u6b21\u5b63\u5ea6\u91cd\u8bad\u7684\u7279\u5f81\u91cd\u8981\u6027\u5b58\u4e0b\u6765\uff0c\u7edf\u8ba1\u6bcf\u4e2a\u7279\u5f81\u8fdb\u5f53\u5b63\u524d\u4e09\u540d\u7684\u9891\u7387\u3002\u6700\u9ad8\u7684\u662f\u91cf\u6bd4 61.6%\uff0c\u6628\u65e5\u6da8\u5e45 52.3%\uff0c5 \u65e5\u6da8\u5e45 34.9%\uff0c\u661f\u671f\u51e0\u4ece\u6765\u6ca1\u8fdb\u8fc7\u524d\u4e09\uff0c0%\u3002<\/p>\n\n\n\n
\u5b83\u786e\u5b9e\u6293\u5230\u4e86\u6570\u636e\u91cc\u771f\u5b9e\u5b58\u5728\u7684\u7ed3\u6784\uff0c\u6bd4\u5982\u6ce2\u52a8\u7387\u7684\u805a\u96c6\u3001\u91cf\u4ef7\u4e4b\u95f4\u7684\u8054\u52a8\u3002\u8fd9\u4e9b\u7ed3\u6784\u5ba2\u89c2\u5b58\u5728\uff0c\u968f\u4fbf\u4ec0\u4e48\u6a21\u578b\u90fd\u80fd\u627e\u5230\uff0c\u53ea\u662f\u4e0d\u6307\u5411\u660e\u5929\u3002<\/p>\n\n\n\n
\u5b83\u5b66\u4f1a\u4e86\u54ea\u4e9b\u7279\u5f81\u4e4b\u95f4\u6709\u5173\u7cfb\uff0c\u6ca1\u5b66\u4f1a\u660e\u5929\u5f80\u54ea\u8d70\u3002\u8fd9\u4e24\u4ef6\u4e8b\u542c\u8d77\u6765\u63a5\u8fd1\uff0c\u5b9e\u9645\u5dee\u5f97\u5f88\u8fdc\u3002<\/p>\n\n\n\n
\u6362\u66f4\u957f\u7684\u5468\u671f\u3001\u6362\u6a2a\u622a\u9762\u3001\u6362\u53e6\u7c7b\u6570\u636e\uff0c\u90fd\u662f\u65b9\u5411\uff0c\u4e0d\u662f\u627f\u8bfa\u3002\u8c01\u8bf4\u6362\u4e2a\u8f93\u5165\u5c31\u80fd\u8dd1\u8d62\uff0c\u8ba9\u4ed6\u5148\u628a\u6821\u51c6\u66f2\u7ebf\u653e\u51fa\u6765\u3002<\/p>\n\n\n\n
\u516b\u3001\u89c2\u70b9\u603b\u7ed3<\/strong><\/h2>\n\n\n\n
\u56de\u5230\u6700\u5f00\u59cb\u90a3\u4e2a\u95ee\u9898\u3002\u6280\u672f\u6307\u6807\u8fd8\u6709\u6ca1\u6709\u7528\u3002<\/p>\n\n\n\n
\u6211\u53d1\u73b0\u81ea\u5df1\u539f\u6765\u7684\u95ee\u6cd5\u662f\u6b6a\u7684\u3002\u6307\u6807\u6709\u6ca1\u6709\u7528\u662f\u8868\u9762\u95ee\u9898\uff0c\u6211\u771f\u6b63\u60f3\u95ee\u7684\u662f\uff1a\u80fd\u4e0d\u80fd\u9760\u5b83\u4eec\u731c\u51c6\u660e\u5929<\/strong>\u3002\u8fd9\u4e24\u4ef6\u4e8b\u4e0d\u662f\u4e00\u56de\u4e8b\u3002<\/p>\n\n\n\n
\u6307\u6807\u6709\u7528\u3002\u5b83\u4eec\u80fd\u544a\u8bc9\u4f60\u8fc7\u53bb\u53d1\u751f\u4e86\u4ec0\u4e48\u3001\u73b0\u5728\u7684\u6ce2\u52a8\u6bd4\u4e0a\u4e2a\u6708\u5927\u8fd8\u662f\u5c0f\uff0c\u4e5f\u80fd\u8ba9\u4f60\u9762\u5bf9\u540c\u4e00\u4e2a\u4f4d\u7f6e\u65f6\u4fdd\u6301\u4e00\u81f4\u3002<\/p>\n\n\n\n
\u660e\u5929\u6536\u76d8\u6bd4\u4eca\u5929\u9ad8\u5417\uff1f\u8fd9\u4e2a\u95ee\u9898\uff0c\u4ef7\u683c\u548c\u6210\u4ea4\u91cf\u56de\u7b54\u4e0d\u4e86\u300211 \u4e2a\u6307\u6807\u4e0d\u884c\uff0c\u6362 20 \u4e2a\u4e5f\u4e0d\u884c\uff1bLightGBM \u4e0d\u884c\uff0c\u66f4\u6df1\u7684\u7f51\u7edc\u5927\u6982\u7387\u4e5f\u4e0d\u884c\u3002\u4e0d\u662f\u6a21\u578b\u4e0d\u591f\u806a\u660e\uff0c\u662f\u8fd9\u4e2a\u95ee\u9898\u80fd\u7528\u7684\u4fe1\u606f\u672c\u6765\u5c31\u8fd9\u4e48\u5c11\u3002<\/p>\n\n\n\n
\u60f3\u901a\u8fd9\u4e00\u70b9\uff0c\u5927\u5bb6\u5e94\u8be5\u53cd\u800c\u8e0f\u5b9e\u4e86\u3002\u4ee5\u524d\u603b\u89c9\u5f97\u505a\u4e0d\u51fa\u7a33\u5b9a\u7684\u6a21\u578b\u662f\u81ea\u5df1\u4e0d\u591f\u52aa\u529b\uff0c\u53c2\u6570\u6ca1\u8c03\u597d\u3001\u7279\u5f81\u6ca1\u9020\u5168\u3001\u6570\u636e\u6ca1\u627e\u5bf9\u3002\u73b0\u5728\u77e5\u9053\u4e0d\u662f\u3002<\/p>\n\n\n\n
\u90a3\u4e2a\u6a21\u578b\u6211\u6ca1\u5220\uff0c\u7559\u5728\u6587\u4ef6\u5939\u91cc\u3002\u51c0\u503c\u66f2\u7ebf\u8dd1\u8f93\u4e00\u76f4\u6301\u6709\uff0c\u6821\u51c6\u66f2\u7ebf\u662f\u4e00\u6761\u5e73\u7684\u7ebf\uff0c\u90fd\u4e0d\u7b97\u5149\u5f69\u3002\u4f46\u5b83\u62e6\u4f4f\u4e86\u4e00\u4e2a\u5ff5\u5934\uff0c\u90a3\u4e2a\u518d\u52aa\u529b\u4e00\u70b9\u5c31\u80fd\u731c\u51c6<\/strong>\u7684\u5ff5\u5934\u3002<\/p>\n\n\n\n
\u8fd9\u7bc7\u5c31\u5230\u8fd9\u3002\u5982\u679c\u4f60\u624b\u4e0a\u4e5f\u6709\u4e00\u4e2a\u51c6\u786e\u7387\u8fd8\u4e0d\u9519<\/strong>\u7684\u6a21\u578b\uff0c\u6211\u60f3\u8bf7\u4f60\u505a\u4e00\u4ef6\u4e8b\uff0c\u5728\u5b83\u7684\u51c6\u786e\u7387\u65c1\u8fb9\u5199\u4e0a\u5e02\u573a\u7684\u57fa\u51c6\u7387\u3002\u4e24\u4e2a\u6570\u5b57\u653e\u4e00\u8d77\uff0c\u5b83\u503c\u591a\u5c11\u5c31\u6e05\u695a\u4e86\u3002<\/p>\n\n\n\n
\n\n\n\n
#\u673a\u5668\u5b66\u4e60<\/a> #LightGBM<\/a> #\u91cf\u5316\u4ea4\u6613<\/a> #SPY<\/a> #\u6280\u672f\u6307\u6807<\/a> #\u56de\u6d4b<\/a> #\u8fc7\u62df\u5408<\/a> #\u6821\u51c6\u66f2\u7ebf<\/a> #\u57fa\u51c6\u7387<\/a> #\u91cf\u5316\u7814\u7a76<\/a> #Python<\/a> #\u6a21\u578b\u8bc4\u4f30<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"
\u4f5c \u8005\uff1a\u8001\u4f59\u635e\u9c7c \u539f\u521b\u4e0d\u6613\uff0c\u8f6c\u8f7d\u8bf7\u6807\u660e\u51fa\u5904\u53ca\u539f\u4f5c\u8005…<\/p>\n
Continue reading\u628a\u7b54\u6848\u6253\u4e71\u5582\u7ed9\u6a21\u578b\uff0c\u5b83\u7167\u6837\u51c6\u786e\u7387 55%<\/span><\/a><\/div>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2],"tags":[17,4,5,6],"class_list":["post-4951","post","type-post","status-publish","format-standard","hentry","category-aiinvest","tag-ai","tag-6","entry"],"_links":{"self":[{"href":"https:\/\/laoyulaoyu.com\/index.php\/wp-json\/wp\/v2\/posts\/4951","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/laoyulaoyu.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/laoyulaoyu.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/laoyulaoyu.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/laoyulaoyu.com\/index.php\/wp-json\/wp\/v2\/comments?post=4951"}],"version-history":[{"count":1,"href":"https:\/\/laoyulaoyu.com\/index.php\/wp-json\/wp\/v2\/posts\/4951\/revisions"}],"predecessor-version":[{"id":4959,"href":"https:\/\/laoyulaoyu.com\/index.php\/wp-json\/wp\/v2\/posts\/4951\/revisions\/4959"}],"wp:attachment":[{"href":"https:\/\/laoyulaoyu.com\/index.php\/wp-json\/wp\/v2\/media?parent=4951"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/laoyulaoyu.com\/index.php\/wp-json\/wp\/v2\/categories?post=4951"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/laoyulaoyu.com\/index.php\/wp-json\/wp\/v2\/tags?post=4951"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}