Practical Applications of AI in eDiscovery

Since the dawn of modern litigation, attorneys have grappled with finding the most efficient and strategic method of producing discovery. However, the shift to computers and electronically stored information (ESI) within organizations since the 1990s exponentially complicated that process. Rather than sifting through filing cabinets and boxes, litigation teams suddenly found themselves looking to technology to help them review and produce large volumes of ESI pulled from email accounts, hard drives, and more recently, cloud storage. In effect, because technology changed the way people communicated, the legal industry was forced to change its discovery process.The Rise of TARDue to growing data volumes in the mid-2000s, the process of large teams of attorneys looking at electronic documents one-by-one was becoming infeasible. Forward-thinking attorneys again looked to technology to help make the process more practical and efficient – specifically, to a subset of artificial intelligence (AI) technology called “machine learning” that could help predict the responsiveness of documents. This process of using machine learning to score a dataset according to the likelihood of responsiveness to minimize the amount of human review became known as technology assisted review (TAR).TAR proved invaluable because machine learning algorithms’ classification of documents enabled attorneys to prioritize important documents for human review and, in some cases, avoid reviewing large portions of documents. With the original form of TAR, a small number of highly trained subject matter experts review and code a randomly selected group of documents, which are then used to train the computer. Once trained, the computer can score all the documents in the dataset according to the likelihood of responsiveness. Using statistical measures, a cutoff point is determined, below which the remaining documents do not require human review because they are deemed statistically non-responsive to the discovery request.Eventually, a second iteration of TAR was developed. Known as TAR 2.0, this second iteration is based on the same supervised machine learning technology as the riginal TAR (now known as TAR 1.0) – but rather than the simple learning of TAR 1.0, TAR 2.0 utilizes a process to continuously learn from reviewer decisions. This eliminates the need for highly trained subject matter experts to train the system with a control set of documents at the outset of the matter. TAR 2.0 workflows can help sort and prioritize documents as reviewers code, constantly funneling the most responsive to the top for review.Modern Data ChallengesBut while both TAR 1.0 and TAR 2.0 are still widely used in eDiscovery today – the data landscape looks drastically different than it did when TAR first made its debut. Smartphones, social media applications, ephemeral messaging systems, and cloud-based collaboration platforms, for example, did not exist twenty years ago but are all commonly used within organizations for communication today. This new technology generates vast amounts of complicated data that, in turn, must be collected and analyzed during litigations and investigations.Aside from the new variety of data, the volume and velocity of modern data is also significantly different than it was twenty years ago. For instance, the amount of data generated, captured, copied, and consumed worldwide in 2010 was just two zettabytes. By 2020, that volume had grown to 64.2 zettabytes.[1]Despite this modern data revolution, litigation teams are still using the same machine learning technology to perform TAR as they did when it was first introduced over a decade ago – and that technology was already more than a decade old back then. TAR as it currently stands is not built for big data – the extremely large, varied, and complex modern datasets that attorneys must increasingly deal with when handling discovery requests. These simple AI systems cannot scale the way more advanced forms of AI can in order to tackle large datasets. They also lack the ability to take context, metadata, and modern language into account when making coding predictions. The snail pace of the evolution of TAR technology in the face of the lightning-fast evolution of modern data is quickly becoming a problem.The Future of TARThe solution to the challenge of modern data lies in updating TAR workflows to include a variety of more advanced AI technology, together with bringing on technology experts and linguistics to help wield them. To begin with, for TAR to remain effective in a modern data environment, it is necessary to incorporate tools that leverage more advanced subsets of AI, such as deep learning and natural language processing (NLP), into the TAR process. In contrast to simple machine learning (which can only analyze the text of a document), newer tools leveraging more advanced AI can analyze metadata, context, and even the sentiment of the language used within a document. Additionally, bringing in linguists and experienced technologists to expertly handle massive data volumes allows attorneys to focus on the actual substantive legal issues at hand, rather than attempting to become an eDiscovery Frankenstein (i.e., a lawyer + a data scientist + a technology expert + and a linguistic expert all rolled into one).This combination of advanced AI technology and expert service will enable litigation teams to reinvent data review to make it more feasible, effective, and manageable in a modern era. For example, because more advanced AI is capable of handling large data volumes and looking at documents from multiple dimensions, technology experts and attorneys can start working together to put a system in place to recycle data and past attorney work product from previous eDiscovery reviews. This type of “data reuse” can be especially helpful in tackling the traditionally more expensive and time-consuming aspects of eDiscovery reviews, like privilege and sensitive information identification and can also help remove large swaths of ROT (redundant, obsolete, or trivial data). When technology experts can leverage past data to train a more advanced AI tool, legal teams can immediately reduce the need for human review in the current case. In this way, this combination of advanced AI and expert service can reduce the endless “reinventing the wheel” that historically happens on each new matter.ConclusionThe same cycle that brought technology into the discovery process is again prompting a new change in eDiscovery. The way people communicate and the systems used to facilitate that communication at work are changing, and current TAR technology is not equipped to handle that change effectively. It’s time to start incorporating more modern AI technology and expert services into TAR workflows to make eDiscovery feasible in a modern era.To learn more about the advantages of leveraging advanced AI within TAR workflows, please download our white paper, entitled “TAR + Advanced AI: The Future is Now.” And to discuss this topic more, feel free to connect with me at smoran@lighthouseglobal.com. [1] “Volume of data/information created, captured, copied, and consumed worldwide from 2010 to 2025” https://www.statista.com/statistics/871513/worldwide-data-created/practical-applications-of-ai-in-ediscovery; ai-and-analytics; ediscovery-reviewai-big-data, tar-predictive-coding, ediscovery-process, prism, blog, data-reuse, ai-and-analytics, ediscovery-reviewai-big-data; tar-predictive-coding; ediscovery-process; prism; blog; data-reusesarah moran

Emerging challenges with big data—large sets of structured or unstructured data that require specialized tools to decipher— have been well documented, with estimates of worldwide data consumed and created by 2025 reaching unfathomable volumes. However, these challenges present an opportunity for innovation. Over the past few years, we’ve seen a renaissance in AI products and solutions to help address and evolve past these issues. From smaller players creating bespoke algorithms to bigger technology companies developing solutions with broader applications, there are substantial opportunities to harness AI and rethink how to manage data.A recent announcement of Microsoft’s Syntex highlights the immense possibilities for, and investment in, leveraging AI to manage content and augment human expertise and knowledge. The new feature in Microsoft 365 promises advanced AI and automation to classify and extract information, process content, and help enforce security and compliance policies. But what do new solutions like this mean for eDiscovery and the legal industry?There are three key AI benefits reshaping the industry you should know about:1. Meeting the challenges of cloud and big data2. Transforming data strategies and workflows3. Accelerating through automationMeeting the challenges of cloud and big data Anyone close to a recent litigation or investigation has witnessed the challenge posed by today’s explosion of data—not just volume, but the variety, speed, and uncertainty of data. To meet this challenge, traditional approaches to eDiscovery need to be updated with more advanced analytics so teams can first make sense of data and then strategize from there. Simultaneous with the need to analyze post-export documents, it’s also clear that proactively managing an organization’s data is increasingly essential. Organizations across all industries must comply with an increasingly complex web of data privacy and retention regulations. To do so, it is imperative that they understand what data they are storing, map how that data flows throughout the organization, and have rules in place to govern the classification, deletion, retention, and protection of data that falls within certain regulated categories of data types. However, the rise of new collaboration platforms, cloud storage, and hybrid working have introduced new levels of data complexity and put pressure on information governance and compliance practices—making it impossible to use older, traditional means of information governance workflows. Leveraging automation and analytics driven by AI advances teams from a reactive to proactive posture. For example, teams can automate a classification system with advanced AI where it reads documents entering the organization’s digital ecosystem, classifies them, and labels them according to applicable sensitivity or retention categories implemented by the organization—all of which is organized under a taxonomy that can be searched later. This not only helps an organization better manage data and risks upfront—creating a more complete picture of the organization’s data landscape—but also informs better and more efficient strategies downstream. Transforming data strategies and workflows New AI capabilities give legal and data governance teams the freedom to think more holistically about their data and develop strategies and workflows that are updated to address their most pressing challenges. For eDiscovery, this does not necessarily mean discarding legacy workflows (such as those with TAR) that have proven valuable, but rather augmenting them with advanced AI, such as natural language processing or deep learning, which has capabilities to handle greater data complexity and provide insights to approach a matter with greater agility. But the rise of big data means that legal teams need to start thinking about the eDiscovery process more expansively. An effective eDiscovery program needs to start long before data collection for a specific matter or investigation and should contemplate the entire data life cycle. Otherwise, you will waste substantial time, money, and resources trying to search and export insurmountable volumes of data for review. You will also find yourself increasingly at risk for court sanctions and prolonged eDiscovery battles if your team is unprepared or ill-equipped to find and properly export, review, and produce the requested data within the required timeline. For compliance and information governance teams, this proactive approach to data has even greater implications since the data they’re handling is not restricted to specific matters. In both cases, AI can be leveraged to classify, organize, and analyze data as it emerges—which not only keeps it under control but also gives quicker access to vital information when teams need it during a matter.Advanced AI can be applied to analyze and organize data created and held by specific custodians who are likely to be pulled into litigation or investigations, giving eDiscovery teams an advantage when starting a matter. Similarly, sensitive or proprietary information can be collected, organized, and searched far more seamlessly so teams don’t waste time or resources when a matter emerges. This allows more time for case development and better strategic decisions early on.Accelerating through automation Data growth continues to show no signs of slowing, emphasizing the need for data governance systems that are scalable and automated. If not, organizations run the risk of expending valuable resources on continually updating programs to keep pace with data volumes and reanalyzing their key information.The best solutions allow experts in your organization to refine and adjust data retention policies and automation as the organization’s data evolves and regulations change. In today’s cloud-based world, automation is a necessity. For example, a patchwork of global and local data privacy regulations (GDPR, California’s CCPA, etc.) include restrictions related to the timely disposal of personal information after the business use for that data has ended. However, those restrictions often conflict with or are triggered by industry regulations that require companies to keep certain types of documents and data for specific periods of time. When you factor in the dynamic, voluminous, and complex cloud-based data infrastructure that most company’s now work within, it becomes obvious why a manual, employee-based approach to categorizing data for retention and disposal is no longer sustainable. AI automation can identify personal information as it enters the company’s system, immediately classify it as sensitive data, and label it with specific retention rules. This type of automation not only keeps organizations compliant, it also enables legal and data governance teams to support their organization’s growth—whether it’s through new products, services, or acquisitions—while keeping data risk at bay. Conclusion Advancements in AI are providing more precise and sophisticated solutions for the unremitting growth in data—if you know how to use them. For legal, data governance, and compliance teams, there are substantial opportunities to harness the robust creativity in AI to better manage, understand, and deploy data. Rather than be inhibited by endless data volumes and inflexible systems, AI can put their expertise to work and ultimately help to do better at the work that matters. practical-applications-of-ai-in-ediscovery; ai-and-analytics; chat-and-collaboration-data; microsoft-365; lighting-the-path-to-better-information-governancemicrosoft, ai-big-data, cloud-security, blog, record-management, ai-and-analytics, chat-and-collaboration-data, microsoft-365,microsoft; ai-big-data; cloud-security; blog; record-managementmitch montoya