Rough Sets Theory for Chinese-listed Companies' Fraudulent Financial Reporting Predictions

The rough sets approach is used to provide a set of rules able to discriminate between law-abiding and defrauded Chinese listed companies in order to predict fraudulent financial reporting firms. The paper uses 767 Chinese listed companies as model samples and 116 Chinese listed companies as test samples, the extracted rules are based on attribute value importance and dominance-based rough sets approach. The results shown the prediction model identified the law-abiding listed companies with 97.8 percent precision, at the same time identified the defrauded listed companies with 66 percent precision. The extracted identification rules reflect the economic laws on fraudulency.