Unverified60% confidenceFactExact time
Marcos López de Prado noted in Advances in Financial Machine Learning that most trading strategies published in academic journals are not statistically significant after controlling for multiple testing.
2
Sources
60%
Confidence
Long-term
Relevance
8/6/2026
First Seen
Sources
Related Claims
Unverified坎贝尔·哈维等学者的研究表明，金融学术文献中大量被发表的因子可能都是回测过拟合或数据窥探偏差的结果69% similarUnverifiedLarge model classification judgments are not 100% reliable, and it is recommended to retain a manual review step for critical financial and legal documents.65% similarVerifiedFinancial markets are characterized by extremely strong non-stationarity and low signal-to-noise ratio, and historical patterns do not necessarily extend into the future.61% similarUnverified金融数据的非平稳性意味着消融结论在一个时段成立未必在另一时段同样有效，这是金融AI消融实验的独特挑战60% similarUnverifiedThe value of corporate data has long been difficult to quantify and is often not included in formal financial statements.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/693316API
curl https://kongchang.com/api/v1/knowledge/claims/693316MCP
get_claim(id=693316)