Due to the sheer volume of electronic information people and businesses now store, the process of eDiscovery in a legal dispute can involve vast amounts of electronically stored information (ESI). One of the best practices in eDiscovery is using software, including artificial intelligence (AI), to automate various stages of the eDiscovery process. This practice frees up legal teams to focus on strategy and higher-level decisions rather than the minutiae of sorting through ESI.
Venio Systems software can be customized to allow for eDiscovery automation at each step outlined by the Electronic Discovery Reference Model (EDRM), a widely used framework for the eDiscovery process. This blog will give an overview of various opportunities for automation in eDiscovery.
Automation in ECA
Before proceeding with the first steps of the EDRM, legal teams will engage in an early case assessment (ECA). This process can look different from one legal dispute to another. It essentially consists of uncovering critical ESI and other documentation as early as possible to best determine the parameters of the dispute, including time frames, strategy, and making important decisions like settling or taking a case to court.
An ECA’s goal is to have the best possible understanding of the data set and determine what risks and liabilities might exist in order to guide decisions about the case.
It’s worth mentioning that although an ECA is generally seen as a preliminary step, it does have a ripple effect on different stages of the EDRM. For example, culling a significant number of irrelevant documents during ECA will decrease processing time once that stage is reached.
During ECA, legal teams will want to engage in preliminary data analysis to get some quantitative information — like how much data there actually is — as well as other insights like keywords, date ranges, and names of custodians who might be interviewed. This kind of analysis can then feed automation in eDiscovery software that will sift through ESI rapidly and generate reports about the contents.
Automation at this stage can also include the use of AI. When AI is discussed in the context of the eDiscovery process, it most often refers to predictive coding. This technology is often touted as being most useful during the later review stage of the EDRM, but it can also be used during early case assessment. It consists of training software with existing data, as reviewers tag documents as relevant or irrelevant, and then algorithms take over. With each iteration, the software “learns” to review the ESI and classify documents independently, with minimal human oversight.
During ECA, as the software learns what is relevant to the case, it can also be set to filter out and exclude data and can be used to automate legal holds. Legal holds are an important part of the later stages of the EDRM, including identification, collection, and preservation. As you read on, you’ll learn how Venio’s software can be used to automate such processes.
How Venio ECA can Automate Preliminary Phases of eDiscovery
Software designed specifically for early case assessment can be implemented to cull up to 90% of irrelevant ESI, significantly accelerating the processing stage later on. With Venio’s ECA software, you can also use the in-place indexing feature to speed up review and analysis later while also reducing network storage and/or cloud hosting.
A complete eDiscovery software solution like Venio’s can also offer accelerated filtering and excluding features. It can initiate indexed data analysis and reporting of visual timelines, email communication, and social network diagrams.
These features allow you to output only the relevant data for processing, which cuts down on review time, which is easily the most costly step of the eDiscovery process. Venio’s platform gives you the option of deploying ECA on-remise or in the cloud.
In addition to ECA-specific software, Venio’s Legal Hold software can be used on its own or as an end-to-end solution to automate legal holds. This helps legal teams efficiently manage custodians and reduce errors inherent in completing the process manually, significantly reducing costs.
Other Early Stages of the EDRM
The first stages of eDiscovery outlined by the EDRM include identification, preservation, and collection. Technically, the first step is information governance; however, that step is more of a framework for eDiscovery rather than an actual step in the process.
After the identification stage, where teams identify relevant ESI — which can be done through things like interviewing custodians and reviewing the overall case data — it needs to be preserved from spoliation. This can involve implementing a legal hold, which is an official notification to individuals or organizations not to delete ESI or dispose of any physical documents that could warrant further investigation.
Next, it’s time for preservation and collection, which must all be done in a legally defensible manner to avoid potential issues in court. Collection can benefit from software to automate the process as it is overseen by IT professionals, Forensic experts, and/or legal teams. Those teams must carefully ensure that the correct ESI is collected. The methods of preservation and collection are often confused but are quite different. Collection can technically be viewed as a preservation method, albeit inefficient. Preservation can rather be thought of as safeguarding against deletion.
What is eDiscovery Processing?
After the preliminary stages are complete, the ongoing phase of processing begins. Essentially it consists of cataloging, error-checking, and indexing the data that has been collected. The early stages are about getting all the data you need, and the processing stage is about organizing it so that it is ready for legal teams to review and analyze.
Another way to think of processing is filtering. At this stage, powerful eDiscovery software can automate deduping, deNIST, identifying near dupes, and making sure data is in a usable form. It can also include imaging, which the processing engine can complete at the push of a button. Processing is typically ongoing throughout eDiscovery, as more ESI may be collected and updated. For that reason, and due to the enormous quantities of ESI, this stage greatly benefits from automation using eDiscovery software.
Venio Makes Processing More Efficient
Processing is easily one of the most software-intensive processes in eDiscovery. It prepares the data to be reviewed and analyzed, and these operations are characterized by more human intervention. Any effective eDiscovery platform will be a joint effort between humans and computers, using powerful technology such as Venio Systems software.
The DeNIST tool used in Venio’s eDiscovery software automatically removes superfluous files based on their file extension and unique digital signature, called a hash value. By checking all of the files against a master list of applications from the National Institute of Standards and Technology (NIST), this tool can safely remove irrelevant or duplicate files. This tool can vastly decrease the amount of ESI left to process.
To keep data adequately sorted so it can easily be referred to during analysis, the production of slip sheets creates placeholders to parse files and keep them organized. Automating this process with Venio Systems allows you to create slip sheets based on different file types during ingestion which, in turn, can control the message and location, and be configured to pull content from any metadata field.
The software can also automatically complete optical character recognition (OCR) for specific file types during ingestion while setting character limit thresholds for automating the OCR of PDF files. Users can even set the Nuance OCR to a specific language. Currently, Venio’s software has 45 different language options. Finally, this powerful eDiscovery automation software gives you control over retry attempts at imaging to decide whether to include an image in the index if one or more pages fail OCR.
Venio’s software also includes tools for processing social network data and has a date gap analysis tool. All of these features and more combine into a complete end-to-end eDiscovery solution.
The eDiscovery process has undergone rapid evolution as technology simplifies processes and automation allows legal teams to focus on higher-level decision-making. Any successful eDiscovery team will not only have powerful software and AI tools at their disposal, but this technology will be complemented by highly trained legal teams who know how to get the most out of their tools. With Venio Systems, you can expect a streamlined user experience and a wide array of options to tailor the eDiscovery process to your needs. When facing litigation, legal teams benefit from tools designed not only for efficiency, but which also provide peace of mind and ensure eDiscovery defensibility through accurate and rigorous processes. Venio Systems offers end-to-end eDiscovery solutions with software at the forefront of computing capabilities, designed to effectively handle each stage of the EDRM and ensure the best possible outcome.
About the Author
Ronnie Johnson, Tonya Mullins & Akshita Singhal
Ronnie Johnson is our VP of Operations with 15 years of experience leading operations teams both domestically and internationally. He has a demonstrated history of success in the legal services industry. Tonya Mullins is our Senior Director of Customer Success. She brings a wealth of eDiscovery experience from sales, project management, software development, and business intelligence. Akshita Singhal is our Sr. Marketing Manager and produces industry-related content to advance legal education and encourage conversation.