Polytope Fraud Theory
该研究提出多面体欺诈理论，通过分析专业做空者的行为训练机器学习模型（XGBoost最佳，召回率72%，F1分数82%），识别财务欺诈的十个异常信号，有助于审计和投资决策。
Polytope Fraud Theory (PFT) extends the existing triangle and diamond theories of accounting fraud with ten abnormal financial practice alarms that a fraudulent firm might trigger. These warning signals are identified through evaluation of the shorting behavior of sophisticated activist short sellers, which are used to train several supervised machine learning methods in detecting financial statement fraud using published accounting data. Our contributions include a systematic manual collection and labeling of companies that are shorted by professional activist short sellers. We also combine well-known asset pricing factors with accounting red flags in financial features selections. Using 80 % of the data for training and the remaining 20 % for out-of-sample test and performance assessment, we find that the best method is XGBoost, with a Recall of 72 % and F1-score of 82 %. Other methods have relatively lower performance, demonstrating the robustness of our results. This shows that the sophisticated activist short sellers, from whom the algorithms are learning, have excellent accounting insights, tremendous forensic analytical knowledge, and sharp business acumen. Our feature importance analysis indicates that potential short-selling targets share many similar financial characteristics, such as bankruptcy or financial distress risk, clustering in some industries, inconsistency of profitability, high accrual, and unreasonable business operations. Our results imply the possible automation of advanced financial statement analysis, which can both improve auditing processes and effectively enhance investment performance. Finally, we propose the Unified Investor Protection Framework, summarizing and categorizing investor-protection related theories from the macro-level to the micro-level. • Our study extends existing accounting fraud theories (Fraud Triangle Theory and Fraud Diamond Theory) by introducing ten abnormal financial practice alarms to detect fraud. • We utilize the shorting behavior of activist short sellers to train supervised machine learning models, with XGBoost performing best (Recall 72 %, F1-score 82 %). • Our research involves manual labeling of companies targeted by professional activist short sellers, combining asset pricing factors and accounting red flags. • We identify key financial indicators of fraud, such as bankruptcy risk, profitability inconsistency, and high accruals, often clustering in certain industries. • Our models suggest the possibility of automating financial statement analysis, enhancing both auditing processes and investment decision-making. • We propose a framework that categorizes investor protection theories at macro, meso , and micro levels and a checklist for real practice.