Whichever name you give it – predictive coding, computer assisted review (CAR), or technology-assisted review (TAR) – predictive coding is an amazing tool in the field of ediscovery. In 2012, the EDRM published a new Computer Assisted Review Reference Model (CARRM) framework to demystify this new technique.
First and foremost, the CARRM strongly emphasizes a planning process, during which the review team should:
- Determine the desired outcome of the predictive coding process
- Build rules and methods specific to the case for both human reviewers and the technology
- Educate the reviewers who are involved in the predictive coding process about those rules and methods
Next, the CARRM identifies a process of coding documents, from which the technology learns and classifies other documents in the corpus, followed by human testing and evaluation. This process is iterative, meaning these steps should continue in a cycle until appropriate retrieval metrics (such as precision, recall and f-measure) are achieved and the initial goals are met. Once the evaluation stage is complete, the predictive coding process can end and the team may move on to the next phase of review.
The benefits of predictive coding compared to human review are plentiful. Predictive coding can reduce time on administration and review, reduce the number of documents reviewed, increase the accuracy of review and even review documents quicker.
The bottom line is that while ediscovery budgets are cut and data volumes are ever-growing, predictive coding can help you save time and money by:
- Finding the right documents quickly
- Sorting documents efficiently
- Confirming the reviewers’ work before production
What to know more? Register for the EDRM Webinar, “EDRM’S New Computer Assisted Review Reference Model (CARRM)-Beyond the Test Drive,” with industry experts George Socha, Herbet Roitbat, Bob Rohlf, and myself. It should be a riveting conversation so be sure to register soon.