False Financial Statements (FFS) have long been a serious problem in China and other Asian countries, which significantly dampen the confidence of the investors. Regardless of listed companies or non-listed companies, the percentage of financial statements that contained false information is quite high, which is one of the major reasons why China stock markets moved in the opposite direction towards its wonderful economic growth over the past few years. The objective of this research is to introduce one statistical technique — Classification and Regression Tree (CART), to identify and predict the impacts of FFS. We survey financial statements manipulation tricks, FFS indicators and FFS detection techniques from both China and international perspective, and further look into ten listed companies with known FFS history in China; combining these findings, we propose key indicators to work with CART. Our analysis includes 24 false financial reports, and 124 non-false financial reports. We use CART to develop two FFS detecting models: CART without industry benchmark and CART with industry benchmark. For supporting comparison, we also build a Logit regression which is a commonly used technique in FFS detecting. We find that CART is effective in distinguishing FFS from non-FFS. Both CART models achieve better accuracy in identifying fraud cases and making predictions than Logit regression does, and CART with industry benchmark is slightly better than CART without benchmark, but it does not always have superior performance. Our CART model also tries to capture the indicators and their combinations that could reflect firms with high possibility of FFS in China.

In this paper, we reported the benefits of using eXtended Markup Language (XML) to support financial knowledge management and discussed number of issues associated with developing an XML-based financial knowledge management system. Current searching engines do not provide sufficient performance in terms of recall, precision, and extensibility for financial knowledge management, because the data represented in HTML format cannot support financial knowledge management effectively. On the other hand, XML provides a vendor-neutral approach to structure and organize contents as XML authors are allowed to create arbitrary tags to describe the format or structure of data. A prototype of XML-based ELectronic Financial Filing System (ELFFS-XML) is developed, and value-added services such as automatic tag generation and cross-linking related information from different data sources are provided to enable knowledge representation and knowledge generation. We compared the XML-based ELFFS with the original HTML-based ELFFS and SEDAR -an electronic filing system used in Canada, and we found that ELFFS-XML is able to provide much more functionalities to support knowledge management. We also compared our automatic tag generation result with the experts' and investors' choices, and recommended some directions for future development of similar electronic filing systems.