Equipped with a highly accurate prediction function, the latest version of the AI ​​review tool “KIBIT Automator” is now available

2022.09.12 Press release

--To the press -

Equipped with a highly accurate prediction function, the latest version of the AI ​​review tool “KIBIT Automator” is now available

Promoting operational efficiency and quality improvement with next-generation e-discovery platform

Masahiro Morimoto, President and CEO
2-12-23 Konan, Minato-ku, Tokyo
(Code number: 2158 TSE Growth)

 FRONTEO Co., Ltd. (Headquarters: Minato-ku, Tokyo, President: Masahiro Morimoto, hereinafter FRONTEO) has classified documents related to evidence in digital forensics and documents that are not related to the self-developed AI review tool "KIBIT Automator". (Reference: Press release "FRONTEO develops algorithm that achieves both ensemble learning and performance prediction in self-developed AI engine KIBIT" https://www.fronteo.com/20220721) , We are pleased to inform you that we have started offering from September 9th.This function improves the accuracy of the cut-off point*¹ for judging "documents that do not need to be read" among the documents to be reviewed, greatly improving the efficiency of review work and enabling an accurate forecast of work time.


 In recent years, with the rapid development of the digital society, the use of IT has become commonplace, and the amount of electronic data managed by companies is steadily increasing.On the other hand, review work in digital forensics (information preservation and analysis investigations targeting information recorded on digital devices) requires work that guarantees both speed and quality within a limited number of work days. The increasing work time, the required quality of investigation, and the huge cost are major issues.


 Since its birth in 2019, KIBIT Automator has undergone various functional enhancements, and in 2021, as a next-generation e-discovery platform to solve these issues, it will start providing consistent services from preprocessing to review of collected data. Did.In addition, an automatic extraction function* for semi-duplicate data (similar data that differs only in part)2We have continuously expanded and improved the functions, such as installing , to improve the service quality.


Figure: Forecast values ​​installed in KIBIT Automator.Predicted and measured values ​​are superimposed for comparison.


 The new function added this time accurately predicts the percentage of documents that need to be reviewed by humans out of all the document data to be reviewed.In the verification, the difference between the predicted value of the required document data ratio at a recall rate of 80% before the start of the review and the measured value after the review was within XNUMX% (Fig.).With this function, it is possible to estimate the work time required for document review with a high degree of accuracy, implement planned review operations based on accurate forecasts, improve operational efficiency, and reduce the strategic planning time of companies and lawyers involved in litigation. It is hoped that this can be secured.It also eliminates the need to create additional evaluation data that was previously required to calculate predicted values.


 As a pioneer of digital forensics and discovery (discovery procedures in the US civil lawsuit system) in Japan, FRONTEO will continue to develop and improve solutions that will help streamline fraud investigations and litigation support, and provide high-quality services. I will come.


*1 Cut-off point: Of the data arranged in order of relevance judged by AI as evidence, if a human confirms the top percentage of the data, the review will not be hindered even if the data after that is not viewed. A number that indicates whether or notThe implementation of the cutoff and the cutoff point are determined on a case-by-case basis in consultation with the attorneys in charge and the person in charge of the company.
*2 Automatic extraction of semi-duplicate data: A function called Near Duplication.Among the data that can be used as evidence, when we discover data to be submitted to the court, consultation matters regarding litigation between clients and lawyers, or data that has been permitted not to be disclosed as trade secrets, we efficiently disseminate similar data. Group and extract well.
*3 Recall Rate: Recall rate.Percentage of data evaluated as “evidentially relevant” out of all surveyed data.
*4 Precision Rate: Relevance rate. Percentage of all data scored as “relevant” by AI that actually contain relevant data.



■ About KIBIT Automator URL: https://legal.fronteo.com/products/kibit-automator/
"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 proceedings of US civil proceedings. An AI tool developed for the purpose, released in March 2019.We apply the research method used in discovery and utilize AI to examine and analyze large-capacity e-mails and electronic files that are evidence materials.In recent years, it is expected to respond to the short-term information disclosure required of companies.


■ About FRONTEO URL: https://www.fronteo.com/
FRONTEO uses the in-house developed AI engines "KIBIT", "Concept Encoder (trademark: conceptencoder, reading: concept encoder)", and "Looca Cross", which are specialized in natural language processing. It is a data analysis company that supports the business of companies by extracting meaningful and important information from a huge amount of text data. 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 (currently TSE Growth) 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).


* FRONTEO, KIBIT Automator, KIBIT, conceptencoder, and Looca Cross are registered trademarks of FRONTEO in Japan.



<Contact for inquiries from the press>

Public Relations Officer, FRONTEO Inc.

Email: pr_contact@fronteo.com


ja 日本語
Machine Translation by Google. : close x