TCR

TCR is a commonly used abbreviation for ‘total

cost of review’ This is the amount spent on a complete e-discovery workflow. A team with Relativity analyzed TCR and has reported its results here.

As the below chart shows:

Review cost still takes up most of the budget, with processing cost coming in a distant second. Collection and hosting fees are minimal.

The study shows that targeted collection will reduce TCR in the long run, if not in the first couple of months.

According to the study, if targeted collection is performed, in the end TCR will be reduced by almost a third.

Jump to Sentences TAR Thinks Make a Document Responsive

Electronic Discovery services provider Fronteo has developed an add-in for Relativity that will help expedite technology assisted review and provide a firmer basis to show that it is actually working. KIBIT Automator highlights individual sentences in a document flagged as being responsive, so a reviewer can easily see which parts of the document the TAR software believes make the document relevant.

Fronteo claims that the speed of the human review necessary for TAR can be more than doubled. KIBIT can also generate heat maps to indicate where documents marked as being non-responsive were coded differently than other documents with a high degree of textual similarity. It performs email threading and uses metadata in its machine learning algorithm.

Fronteo claims that its software can perform email threading on more than 2 million documents within 5 hours.

Email threading is performed on emails which are in Asian languages by making use of systems used in Japan. Fronteo is a Japanese company, so it appears as though this is something it does particularly well.

The Obsolescence of Seed Set TAR

Predictive coding or technology assisted review is often regarded as a process which involves a static 'seed set' that is used as a basis on which to categorize a full document set. A group of documents is identified through manual review. The software trains based on that seed set, which should contain documents which represent key concepts. A QC is done to find an acceptable 'overturn' rate - a low percentage of documents that must be re-categorized by a human reviewer - an indication that an effective seed set has been chosen. A report can be prepared to identify which seed set documents lead to the most overturns, and may need to be removed.

The obsolescence of this type of review (known as TAR 1.0), is evident in Relativity's decision to deprecate sample-based learning, a form of seed set based TAR. After September 2021, it will no longer be possible to run sample-based learning projects in Relativity.

After this September, Relativity will direct its clients to use Active Learning, a TAR 2.0 review process, which uses continUous active learning (CAL) to improve machine learning continuously as manual reviewers make coding decisions.