Stinson Leonard Street LLP
The case team selected OpenText™ Axcelerate™ OnDemand, hosted and managed by OpenText Professional Services, to enhance their review efficiency. Suspecting that there would be a high concentration of produced documents that were not ultimately useful for their litigation strategy, the team identified the important documents faster using Axcelerate’s analytics and machine learning capabilities.
Faster case insights
First, the case team performed an initial sample, gathering a small subset of documents and reviewing them to establish a baseline of relevancy. Next, they conducted some basic culling using Axcelerate’s Smart Filters, Phrase Analysis and keyword searching toolset to reduce the document volume further.
The team then created an input set of documents to begin training Axcelerate Predictive Coding technology, and ran several iterative cycles for machine learning. In each iteration, Axcelerate recommended a priority batch of documents for review, and the team further refined the solution’s training. The review was completed when the team was satisfied, based on the analysis performed, that it had identified the critical documents needed to inform their strategy. To validate, the team analyzed a small sample of the unreviewed content to verify that nothing significant was missed.
Lower review costs
Bill Greene, the partner overseeing the project, commented, “With the massive number of documents produced in modern litigation, it is too costly to try to review every document produced.”
Using Axcelerate’s advanced analytics and Predictive Coding, the review team located the critical documents upon reviewing only 2.3 percent of the total document set, fewer than 30,000 of the 1.3 million documents they received.
“We were very pleased with the efficiency and overall cost savings of OpenText Axcelerate OnDemand,” said Greene.
