--To the press -
FRONTEO achieves 70% reduction in target documents for accounting fraud investigation projects through document reviews using AI
Achieves high comprehensiveness, accuracy and speed that lead to evidence discovery
Masahiro Morimoto, President and CEO
東京 都 港区 港 南 2-12-23
(Code number: 2158 TSE Mothers)
FRONTEO Inc. (Headquarters: Minato-ku, Tokyo, President: Masahiro Morimoto, hereafter FRONTEO) can use the AI review platform "KIBIT Automator" to provide highly accurate evidence in corporate accounting fraud investigation cases. We will identify the document and inform you that we have achieved a significant improvement in work efficiency and achieved a 70% reduction in the target document.
Accounting fraud in a company is a serious problem that affects the relationship of trust with stakeholders such as customers and shareholders, and may affect the survival of the company.In fraud investigation, it is necessary to quickly find documents that may be related to fraud from complicated and huge materials and data within the limited investigation time. FRONTEO utilizes KIBIT Automator for accounting fraud investigations, establishes an appropriate division of labor system between AI and people in work, know-how to maximize efficiency, etc., and carries out investigations promptly and surely, companies and society. It corresponds to the needs of.
In this project, by utilizing KIBIT Automator, 1% of the approximately 70 documents surveyed do not need to be checked by humans, and the survey period has been significantly reduced and streamlined.In addition, one of the difficult points of accounting fraud investigation is that it is unclear at the beginning of the investigation whether there is fraud and what kind of fraud was committed, and it is not clear what viewpoint should be applied at the time of investigation. However, in this survey, we were able to narrow down the appropriate target by using AI, and we were able to find documents that lead to quick evidence and to finish the work early.
In a survey using KIBIT Automator, a sample is first sampled from the documents to be reviewed, and the lawyer determines the relevance of the document based on the necessary viewpoint.In addition, KIBIT Automator learns the decisions there and scores the documents under review according to their relevance.The higher the relevance, the higher the score.By assigning a score, in consideration of various conditions such as required work completion time and accuracy, a person reviews a document with a high score in consultation with a lawyer and a client, and a document with a score below a certain level is only reviewed by AI. It is possible to respond by doing.In addition, in the case of double review by humans and AI, by comparing the analysis results of both, it is possible to identify the target to be reconfirmed with priority when there is a large discrepancy in judgment, and humans. You can prevent omission of confirmation due to misjudgment.
Comments from FRONTEO Technical Fellow Shusaku Nozaki
"Accounting fraud was the most common in the survey cases that FRONTEO responded to using AI in 2021. For listed companies, it is becoming common practice to conduct forensic investigations in the investigation of accounting fraud. The amount of data is expected to continue to increase in 2022, and in order to find the necessary information within a limited time, it is necessary to make effective use of technologies such as AI.
One of the characteristics of accounting fraudulent cases is that it is difficult to narrow down by keyword search alone because there are many viewpoints and it is often unclear whether or not there is fraudulent activity or the type at the time of the investigation.The effect of KIBIT Automator is particularly likely to be demonstrated in such surveys, and even in past cases, the efficiency of the survey was greatly improved as a result of finding documents that could not be found by keyword search and appropriately narrowing down the target documents. We have achieved improvement.
It is expected that the environment will continue to be prone to fraud such as information leaks, such as continuing to work from home.It is important for companies to detect signs of fraud at an early stage and take appropriate measures.In order to minimize the risk of fraud, it is important to establish a system to quickly collaborate with experts in the event of an emergency. "
As a pioneer of digital forensics and discovery in Japan, FRONTEO will continue to develop and improve solutions that help streamline fraud investigations and litigation support in 2022.
■ About FRONTEO URL:URL: https://www.fronteo.com/
FRONTEO uses the in-house developed AI engines "KIBIT", "Concept Encoder", and "Looca Cross" that specialize in natural language processing to extract meaningful and important information from a huge amount of text data, and is a company. It is a data analysis company that supports the business of. Since its establishment in August 2003, it has been expanding globally to Japan, the United States, South Korea, and Taiwan, focusing on legal tech businesses such as "e-discovery (electronic discovery)" and "digital forensic investigation" that support corporate international litigation. Has been deployed.Based on the AI technology cultivated in this business, we will expand the business field to the life science field, business intelligence field, and economic security from 8, and by using AI to "turn text data into knowledge", We contribute to solving various corporate issues such as drug discovery support, dementia diagnosis support, financial, personnel, and sales support. Listed on TSE Mothers on June 2014, 2007. Obtained a first-class medical device manufacturing and sales business license in January 6 (permit number: 26B2021X1), and notified the managed medical device sales business in September of the same year (notification number: 13 Minato Misei Equipment No. 1).The capital is 10350 thousand yen (as of March 9, 3).
■ About KIBIT Automator URL:URL: https://www.fronteo.com/products/kibit/
"KIBIT Automator" improves the efficiency of document review work in electronic discovery (e-discovery), reduces the burden on workers, and reduces costs, among other discoveries required in the trial procedure of US civil proceedings. An AI tool developed for the purpose, released in March 2019.Applying the research method used in discovery, AI is used to examine and analyze large-capacity e-mails and electronic files that are evidence materials.In recent years, it has been utilized as one of the important processes of digital forensic surveys in the surveys of third-party committees in Japan, and it is expected to respond to the short-term information disclosure required by companies.
* FRONTEO, KIBIT, and concept encoder are registered trademarks of FRONTEO in Japan.