The views expressed in this blog are those of the owner and do not reflect the views or opinions of the owner’s employer. All content provided on this blog is for informational purposes only. The owner of this blog makes no representations as to the accuracy or completeness of any information on this site or found by following any link on this site. The owner will not be liable for any errors or omissions in this information nor for the availability of this information. The owner will not be liable for any losses, injuries, or damages from the display or use of this information. This policy is subject to change at any time. The owner is not an attorney, and nothing posted on this site should be construed as legal advice. Litigation Support Tip of the Night does not provide confirmation that any e-discovery technique or conduct is compliant with legal, regulatory, contractual or ethical requirements.
Avenir Light is a clean and stylish font favored by designers. It's easy on the eyes and a great go to font for titles, paragraphs & more.
Relativity Analytics for Small Data Sets
Relativity recommends the use of analytics (email threading; clustering; concept searching; etc.) even for projects where a large amount of ESI is not collected.
Two scenarios show how analytics can help a team get a handle on a matter in just a few days.
A company wanted to conduct an investigation after the sudden departure of two executives, who were suspected of taking proprietary information. In just 5 days the following steps were performed:
1. Email threading brought down the number of email messages to be reviewed by 30%.
2. Communication analysis quickly showed which employees were communicating directly with each other. The larger nodes indicated a greater number of communications.
3. Clustering grouped together conceptually similar documents in the data set.
4. Active learning - TAR - narrowed down a set of documents considered the most likely to be responsive.
5. Relativity's Case Dynamics includes a Timeline Builder that was used in a report to the client.
In a different project, a team was asked to review a data set for which no metadata was been included, and which had a lot of duplicate files. The data was quickly culled down to what needed to be reviewed in just 5 days.
1. The Find near duplicates tool was used to remove a significant percentage of documents.
2. Clustering detected documents groups which were clearly of no interest.
3. The Find Similar Documents analytics tool was used to find dozens of documents which are similar to a handful known to be relevant.
4. Pivot charts showed groups of electronic files which were outliers in the overall set.
5. The documents set was narrowed down further to only the custodians whose data was at issue in the matter. Relativity recently decided to use the term 'entity' for custodian - for some reason.