1. Symantec/
  2. Transparent Predictive Coding

Transparent Predictive Coding

The eDiscovery game is changing.

Transparent Predictive Coding

Transparent Predictive Coding enables review teams to achieve highly accurate results and reduce risk during electronic discovery review. Complete visibility into the prediction process enables users to make informed decisions with confidence in the defensibility of results.
Key Benefits of Transparent Predictive Coding
  • Reduce review cost by up to 98%
  • Accelerate review timeframes
  • Verify accuracy using built-in statistical sampling
  • Ensure the defensibility of the review process

Key Features

A feature of the Symantec Review & Production Module, Transparent Predictive Coding is fully integrated into the Symantec eDiscovery Platform and used to enhance traditional linear review.
Training Source Analytics — Offers sophisticated analytics by custodian, discussion, concept, participant and other criteria ensure the selection of highly relevant initial training sets.
Directed Training — Leverages patent-pending active learning technology to automatically suggest subsequent training sets.
Prediction Insight — Automatically provides a prediction score for the document under review, displaying content and metadata relevant to the prediction.
Review Quality Control — Provides a built-in quality control workflow to assess and improve review accuracy of technology-assisted review.
Advanced Sampling — Built-in statistical sampling tools allow users to select the correct random sample based on the accuracy requirements of each case.
Review Quality Control — Provides a built-in quality control workflow to assess and improve review accuracy of technology-assisted review.
Advanced Sampling — Built-in statistical sampling tools allow users to select the correct random sample based on the accuracy requirements of each case.
Prediction Templates — Import and export prediction models to leverage predictive intelligence across cases.

How Technology-Assisted Review Works

Three Phases of Transparent Predictive Coding:
Transparent Predictive Coding
The Transparent Predictive Coding process begins with a set of judgmentally selected training documents. Reviewers tag these documents based on the unique tagging structure for a particular case. The eDiscovery Platform learns specific criteria that are common for each tag and generates a prediction model that can be applied to the rest of the case documents. Upon completion of the prediction process, users access a variety of prediction accuracy metrics to help evaluate prediction success and determine whether iterations are required to enhance the model.
Transparent Predictive Coding uses patent-pending machine-learning technology to automate accuracy improvements. Many industries use similar machine-learning technology for a range of activities, from filtering email spam to generating personalized recommendations on shopping websites. With Transparent Predictive Coding, Symantec is the first provider to devise a machine-learning model that is specifically designed for the unique needs of eDiscovery.

When to Use Transparent Predictive Coding

Customers use predictive coding in different ways, depending on budget, timeline, and risk profile. The three most common approaches are:
  1. Fully Automated Workflow — Use Transparent Predictive Coding to complete an entire review workflow with the highest cost savings compared to traditional linear review.
  2. Accelerated Linear Review — Use predictive coding to identify high priority documents for manual review or batch documents to different reviewers based on prediction score to speed linear review.
  3. Improved Culling — Before review begins, apply prediction models across cases to more accurately identify and set aside non-responsive items such as junk emails, system messages, and other irrelevant files.

Is Transparent Predictive Coding Defensible?

As legal teams look to new technologies like predictive coding to enhance the review process, they often ask whether these technologies are defensible. If their use is challenged by opposing counsel in court, parties will have to explain and defend their approach. To minimize the risk of disagreements, the Sedona Conference Cooperation Proclamation¹ encourages parties to cooperate with opposing counsel during the initial stages of the case and reach an agreement on the methods and technology that will be used. While cooperation reduces the risk of disagreements, parties will need to explain and defend their approach if consensus is not met.
In commenting on the defensibility of predictive coding, Judge Andrew Peck² has outlined three key questions that parties should be able to address:
  1. What was done?
  2. Did the process produce defensible results?
  3. Did the process produce "responsive documents with reasonably high recall and high precision?"
Transparent Predictive Coding is the first technology to include how predictions are generated, allowing reviewers to make more consistent and accurate review decisions. Using Prediction Insight, reviewers have visibility into why a tag was predicted for the document under review, including document content that supports the prediction. This visibility helps ensure that reviewers make accurate decisions and legal teams can defend review workflows. A quality control workflow enables users to measure review accuracy, identify inconsistent tagging, view disagreements, and compare predictions and human decisions to assess and improve review accuracy.
Every decision reviewers make is tracked in an exportable report to demonstrate process integrity to the court. Take control of the review process with highly accurate and defensible results using the Symantec eDiscovery Platform with Transparent Predictive Coding.

Behind Transparent Predictive Coding

Through the design and development of the Transparent Predictive Coding workflow, Symantec developed unique insights into technology-assisted review.

Predictive Coding Quick Hit Videos

Predictive Coding Quick Hits Video
Visit the Seventh Circuit Pilot Program's Resources Page for more videos from the Mock Trial.

Recent Articles

Visit the Symantec eDiscovery Blog for breaking news on predictive coding matters.
  • Twitter
  • Facebook
  • LinkedIn
  • Google+
  • YouTube