Equivio Relevance

Predictive Coding

Equivio Relevance organises a collection of documents by relevance. Based on initial input from the litigation expert, Equivio Relevance uses statistical and self-learning techniques to calculate graduated relevance scores for each document in the data collection.

Equivio Relevance is a 'lawyer-guided system':

• An expert reviews a sample of documents, ranking them as relevant or not.
• Based on the results, Equivio learns how to score documents for relevance.
• In an iterative, self-correcting process, Equivio feeds additional samples to the expert. These statistically generated samples allow Equivio Relevance to progressively improve the accuracy of its relevance scoring.
• Once a threshold level of accuracy is achieved, Equivio ranks the entire collection, calculating a graduated relevance score for each document.

  Case Study: Predicting the future of discovery | Phonecast: Moeskops on Predictive Coding

  Call +44 (0)20 7422 8850 | Request more information | A4 Brochure [PDF]

Key Benefits

• Reduced costs. Equivio directs the reviewer to the most relevant data, which typically represents only a small percentage of the entire collection.
• Accelerated review. The Equivio technology enables almost immediate access to the relevant data in the collection, accelerating the review process and allowing the team to move much faster in building the case strategy.
• Enhanced review quality. Equivio systemises the quality assurance process for litigation review. Instead of random checks, Equivio identifies documents where there is a discrepancy between the software and the human review team's assessment of relevance.
• Enhanced keywords. Where keywords are used for data culling in the e-disclosure process, the keywords extracted by Equivio Relevance are used to enrich the keywords list generated by the litigation team.
• Early case assessment: By zooming in on the most relevant documents, Equivio Relevance enables informed assessments of the risks and costs of a case. Equipped with a clear view of the strengths and weaknesses of the case, the team is well placed to make decisions on case strategy.
• Culling: In today's e-disclosure environment, the most widely-used culling technique is keyword matching. Research studies show that keyword search techniques typically retrieve 20-30% of the relevant data. Equivio Relevance consistently retrieves 80-95% of the relevant data. The ability of Equivio Relevance to distinguish between relevant and non-relevant documents means that, in total, fewer documents need to be reviewed manually, but 3 to 4 times the number of relevant documents are retrieved.
• Litigation review:
  • First-pass review: Equivio Relevance is widely used as a replacement for first-pass review. Equivio Relevance consistently achieves the same or better accuracy than first-pass human review, but in a fraction of the time and at a fraction of the cost.
  • Prioritised review: By organising the review set according to relevance rankings, Equivio enables prioritisation of document review. This allows attorneys to immediately focus on the most relevant documents, working their way back to the less relevant documents as the review progresses. 
  • Review quality assurance: By identifying discrepancies in the responsiveness designations of Equivio Relevance vis-a-vis the human review team, the application helps find responsive documents missed in the manual review process.
• Intelligence: Equivio Relevance is used by intelligence analysts to focus their research on documents most likely to yield useful data.

  Case Study: Predicting the future of discovery | Phonecast: Moeskops on Predictive Coding

  Call +44 (0)20 7422 8850 | Request more information | A4 Brochure [PDF]