Continuous Active Learning (CAL) is one of the more recent incarnations of predictive coding and removes the need for upfront training sessions, as it categorises and prioritises the remaining documents 'on the fly.'
This is a great article by Lizzie Hancock and Ed Spencer at Taylor Wessing looking at how it can be used most effectively. One of the greatest benefits we have seen of this technology is in respect of investigations, where the system learns as the investigation proceeds and allows for instant access to the core documents, rather than going through training sets.
However, as ever, there are challenges associated with the use of CAL and before using it in anger you really need to understand what the technology is doing and how you are going to use it in the context of the wider review exercise, in order for the concept to yield useful results.
To quote the authors final words: "Technology should be assisting your review, so don’t be afraid to use it!"
Technology assisted review, or predictive coding as it is often called is becoming more and more advanced. It will, or should, in the near future become a part of every document review exercise in some capacity. One of the most talked about innovations in technology assisted review is continuous active learning (CAL). Understanding how this technology can be applied to document review exercises in disputes or investigations is fundamental to getting to the most relevant documents at the earliest stage whilst also keeping costs down.