Legal Analytics & How Attorneys Use It

Legal analytics is the application of data science to the business and practice of law. It is an umbrella term that covers numerous different techniques, legal analytics software, and goals. Legal analytics can be applied directly to the business of law, and it can also be applied to legal work. 

The benefits of legal analytics include saving time, reducing risk, improving decision-making, and increasing goodwill and trust from clients. Legal practitioners may work directly with a legal analytics firm, or they may rely on tools that incorporate legal analytics.

To perform legal analytics, developers and practitioners draw on concepts and tools from the field of data science. At its core, data science is the process of inspecting, cleansing, transforming, and modeling data to discover useful information, inform conclusions, and support decision-making. 

Initially, analytics may focus on summarizing data to provide a new view of historical trends. Beyond presenting basic statistics, data science can inform decisions in the present or about the future. Most of these questions tend to be one of five types:

Within the field of data science are a number of concepts, many of which have become popularized in the media and with vendors. Understanding the meaning of these terms is very helpful when selecting and using legal analytics.

One of the most ubiquitous terms used today in the field is Artificial Intelligence, or simply AI. There isn’t a universal definition for AI. Generally, artificial intelligence is the use of computers to perform human-like tasks. The term is broad and includes the technology behind self-driving cars and film recommendations. Within AI are a number of other concepts. One form of AI that is particularly relevant to the law is Natural Language Processing or NLP. NLP is about teaching computers to read and write. Like NLP, Computer Vision programs allow computers to “see” pictures and videos. Computer Vision is used to identify objects (e.g., it is a cat), recognize people and places, and create models of the world (e.g., for self-driving cars).

All artificial intelligence relies on algorithms or equations. When these algorithms are developed and refined by the computer itself, we are talking about the field of Machine Learning or ML. In ML, data scientists often feed large quantities of data to their algorithms in order to “train” the model. Models are at the heart of machine learning. 

When artificial intelligence projects involve extremely large or complex datasets, we are talking about “big data,” which involves specialized tools and techniques to avoid overloading systems.

In order to do quality legal predictive analytics, one typically needs large amounts of consistent and quality data. Most of the time, this data isn’t clean and neatly waiting for the data scientist. Instead, data engineers often inspect, structure, integrate, clean, and transport the data to a place where it can be used by legal analytics teams.  

All of these techniques fall within legal analytics and are used by developers and business intelligence teams to develop tools and reports to empower legal professionals to do their work better and faster.

Currently, the market for legal analytics tools and services is fragmented as numerous startups and existing companies develop and refine new tools or enter the legal market. Many existing tools are being adapted to the legal market. Practitioners, lawyers, and legal operations managers should keep an open mind and seek advisors to evaluate and implement legal analytics tools.

Like any business, law firm analytics and general counsel can use business analytics tools to gain visibility into their operations and finances. Often this visibility can uncover profit and cost centers in the organization, identify bottlenecks in business processes, and support a host of other executive and operational decision-making. These tools aggregate, model, analyze, and present data from systems across the enterprise (e.g., contract management, CRM, and eDiscovery). 

The market leader in this space is Microsoft with their PowerBI software. However, many vendors provide quality tools. Successfully implementing these kinds of tools often hinges on quality change management rather than tool selection, but here are several to choose from that can meet different needs:

These tools didn’t start as legal technology, but they can be very useful legal analytics tools. CRM allows businesses to develop and track customer engagements, contacts, sales pipelines, customer contracts, and other aspects of the relationship in one place. These tools can be used to perform conflict checks, bill clients, track communications with clients, offer internal and client-facing knowledge bases, and do a multitude of other things. 

The data stored within these systems can be easily analyzed to provide insights into relationships, sales, and performance. Through integration, the data in these systems can support other data analytics in legal industry work, including document automation.

The market leader in CRM tools is Salesforce. Salesforce, which is not specifically targeted to the legal market, has transitioned from software as a service (saas) to platform as a service (paas), where customers and third-party developers can create their own solutions within the Salesforce CRM. For example, Litify is a CRM and document-management application built for the legal market that was developed using the Salesforce CRM tools. There are a number of other CRM tools built specifically for the legal market, including Clio.

Legal departments and law firm data analytics spend considerable time creating and managing document templates. Document automation simplifies this process, reducing errors and saving time. 

Document automation software often includes:

Most of these algorithms are baked into the document automation software and are nearly invisible to many users. However, they are integral to the functionality of the tool.

To create a new legal document, a practitioner can use questionnaires created and managed by the tools to gather the information needed before the software automatically generates the draft document. Subsequently, the practitioner can customize the documents. Legal document automation tools regularly update their library of terms as laws change, nearly eliminating version control issues.

There are many document automation tools that legal practitioners can implement, and many of them provide both document automation and contract review. Current tools in this space include:

During contract negotiation, documents are often emailed back and forth and revised again and again. Tracked changes are turned on and off, changes are accepted and not tracked, and too often scriven errors make their way into agreements, leading to later confusion and client dissatisfaction. 

Contract review tools built using Natural Language Processing allow lawyers to quickly identify problem areas within contracts, saving time and eliminating costly errors. These tools enhance the contract review process by finding inconsistencies, identifying missing clauses, and highlighting risky areas within the contract. Like most legal analytics tools, they supplement and improve rather than eliminate the work of lawyers on contract review.

Contract review tools can either be integrated into contract management tools or stand-alone. Stand-alone tools tend to be less expensive and more flexible, particularly when working with documents from external parties that must be reviewed using standard document software.

A contract review tool, Loio, cuts down the time and effort traditionally associated with reviewing legal agreements. It uses artificial intelligence to quickly analyze contractual documents.

Artificial intelligence tools are used to calculate risk and reward scores for cases. These tools help litigators estimate the likelihood of success for a case, improving decision-making by legal practitioners and clients. 

AI tools can help with:

To develop these kinds of tools, developers need access to large datasets that include information about cases, attorneys, judges, settlements, and more.

An emerging area of AI legal analytics technology is litigation prediction. Many insurance companies and firms use this software to identify cases that could be litigated. This is a less mature area within legal data analytics. 

Current companies in this space include: 

Discovery can account for a majority of the cost in large litigation cases. The process of manually reviewing documents is time-consuming and prone to error. Legal analytics integrated into electronic discovery tools can extract entities from documents, logically organize and display materials, and help lawyers sift through the mountains of discovery. 

Current companies in this space include:

Protecting Intellectual Property (IP) requires considerable effort to monitor and enforce trademark rights. IP protection tools use Computer Vision (a computer that can “see”) and NLP to monitor numerous platforms for trademarks that may infringe on senior trademarks and alert the owner to them. These tools can also alert users to the misuse of trademarks.

There are several trademark screening and protection tools offered by companies, including:

A number of direct-to-client tools are being offered that allow clients to receive services that previously would have been the exclusive domain of lawyers. Many of these tools integrate legal analytics algorithms to improve the user experience. While many lawyers may resist these tools, savvy lawyers can find ways to integrate them into their practices. 

These tools include:

There are many new and exciting legal analytics tools available right now, and more are being launched every week. These tools have the potential to change the practice of law, increasing productivity, reducing errors, and improving client satisfaction. 

Successfully implementing new technology requires particular attention when selecting the technology. When selecting and implementing these tools, it is important that the new tools enhance, rather than disrupt, business processes. To increase the chances of successful implementation, carefully evaluate the available tools and have the right technical and change-management support to integrate the technology, modify business processes, and train and communicate with staff.