Skip to content

The 2020 toolkit: Tech that will upgrade your eDiscovery efficiency

| Written by Altlaw

Dramatically streamline your litigation operations and unlock new, company-wide efficiencies with these advanced eDiscovery tools and systems.

As we roll into 2020, the landscape of litigation looks set to go on as it has done unapologetically for the last fewyears, continuing to burgeon with an abundance of data in new and ever-changing formats. Over time as the market continues to grow in size, scale and complexity, it is safe to say that having access to a suite of sophisticated tools and systems will be practically essential to managing and dealing with any eDiscovery project…as linear approaches will be rendered obsolete.

But that day is yet to arrive. So for now, market-leading eDiscovery tools and technology platforms can instead offer Associates and other key legal team decision makers the opportunity to dramatically streamline their operations, enabling them to do more in the hours they have, and deliver a level of client satisfaction that simply can’t be matched by the firm next door.
Without further ado, let’s look at the best tech features, systems and tools to have in your arsenal for 2020 if you want to unlock new operational efficiencies and deliver a higher-value service to your clients more swiftly than ever before.

Active Learning TAR

TAR (or Technology Assisted Review) is the linchpin of tech-enabled efficiency gains for discovery, automating and dramatically streamlining the formerly resource-heavy document review process.
While the initial iteration of TAR or predictive coding provided game-changing impact in terms of reducing the time and internal resource needed to review documents, it still demanded a base level of man hours and technical expertise from someone to program it and create training sets that allowed the technology to do its job effectively.
Active Learning TAR (or TAR 2.0) brings greater automated efficiency than its predecessor with the additional benefits of machine learning and AI, meaning little to no administrative support is needed for set up, control and maintenance.
As more document coding decisions are made, the system will use them to refine its own understanding of what is relevant, growing faster and more effective as the project goes on.
The exponential gains in effectiveness and efficiency offered by Active Learning TAR can prove a big helping hand in the face of vast volumes of unstructured data and tight deadlines.

Cloud Software

Many in the field of eDiscovery have notably resisted acknowledging the benefits of cloud software, but the truth is, there are an awful lot.
Rapid developments in cloud-based eDiscovery software seem to be presenting the cloud as the more robust choice when compared to on-premise servers.
By opting for cloud systems over on premise, you can drastically reduce the disruption caused by ongoing maintenance and system upgrades. Cloud systems can always ensure you are on the latest version of your software – no IT consultants required.
The sheer scalability offered by cloud eDiscovery also allows you to retain swift and smooth performance regardless of project size or data volume – not to mention it is vital for multi jurisdictional practices or teams servicing a global network of clients and contacts who want to keep their service seamless.
Most cloud platforms worth their salt will also come with an app, which means projects can proceed despite the busy lifestyles and travelling schedules of key decision makers – they can access and interact with information as needed, wherever they are in the world.
Finally, cloud systems offer the chance for legal teams to unify and consolidate all their data and systems, ensuring time is far better spent internally – less time lost downloading files multiple times or sending different versions back and forth, and having all team members collaborating in one place will likely help to keep inter-department communications strong without the need for physical meetings.

Analytics Tools: Email threading

Email Threading can massively reduce the time and complexity of review processes by intuitively grouping case emails, including all forwards, replies, and reply-all messages.
Email threading tools can also identify email relationships (ie specific conversations, how emails relate to key individuals involved in a case, as well as email attachments) and extracts and normalise email metadata.
The analytics engine can also determine which emails belong to the same thread group, overcome and correct any data inconsistencies (such as timestamp differences generated by different servers) and then determines which emails contain relevant content that should be reviewed.
Overall, this significantly ramps up the speed at which one can conduct an intelligent investigation, and find the most relevant, content-rich information from a batch of data.
For those looking to achieve accuracy and precision, while remaining sure that they looked through all of the information available, analytics tools can allow teams to narrow down the document list and cut redundant content without missing any crucial information.

Analytics Tools: Clustering

Clustering tools go beyond the standard keyword and key phrase searches, allowing users to group documents based on their conceptual or contextual similarity – unlike typical categorisation tools however, clustering requires very little manual input as it uses smart technology, it is therefore another great addition to the toolkit for streamlining your internal operations and workflows.
How your case documents are organised for review is an undeniably decisive factor in the efficiency and accuracy of your review, as well as how much it costs your business.
This process of organising documents with similar content into “clusters” can help reviewers make quicker decisions and promote consistency and make manual review processes far more consistent, generally reducing the scope for human error and, indirectly, any potential need for corrections or duplicate effort.

Analytics Tools: Near duplicate detection

Near duplicate detection is a textual analytics tool available from many eDiscovery solutions, which works on what we refer to as ‘structured’ analytics rather than ‘conceptual’ analytics.
One problem with certain reviewing technologies is that they measure the similarity of documents by their ‘hash value’ (a unique numeric value that is more related to the format of a piece of data than its substance) rather than their actual written contents.
Say for example you have two copies of an email within a data batch, one formatted normally, but the other version is formatted as a PDF. Despite them both containing the exact same text, the hash values of these two files would be completely different.
By honing in on the textual content of the data itself, regardless of format, near-duplicate identification will catch similarities like these. This can greatly accelerate the speed of document review while improving accuracy, significantly so when used in conjunction with TAR of large volumes of documents at once, or where large volumes of significant hard copy documents have been digitised.
If you’re currently struggling with the efficiency of your eDiscovery processes, contact us today and a member of our specialist eDiscovery team will be in touch.