Skip to content
Legal Technology

Data Analytics: Driving value at the intersection of internal and external data

Glenn LaForce  Global Director of Knowledge & Research / Shearman & Sterling LLP

· 6 minute read

Glenn LaForce  Global Director of Knowledge & Research / Shearman & Sterling LLP

· 6 minute read

The more law firms can provide quality data analytics to our users, then the better decisions our lawyers can make in bringing added value to our clients

What a year 2020 was, to say the least. The legal industry was caught off-guard by the COVID-19 pandemic, resulting in redundancies, salary cuts, receivable reductions, and more due to the pandemic’s ensuing global economic downturn.

All the while, both clients and law firm leaders held onto the expectation that despite the crisis, they could still derive greater value and profitability, respectively. As the legal industry moved into a remote working environment, industry observers began to see a change in the speed at which law firms were willing to accept innovation. Previously, ideas and technology that were taboo subjects — such as the move to the “cloud” — now, became the norm. Much like baseball in the early 2000s, the desire to leverage analytics to better manage both individual matters and the overall business took off.

Law firms quickly felt the need to begin new analytics programs or accelerate existing ones to meet clients’ everchanging demands. In order to successfully leverage analytics to make decisions, however, quality data is needed from a variety of different sources, both internal and external to a law firm.

In most analytics programs there is pressure from stakeholders to show results quickly. They want a sexy interface that shows graphs and trends to help them drive decisions. But, if the integrity and quality of data that is feeding the interface isn’t good, then the user is left making poor decisions from bad data, and ultimately the program fails.

At Shearman & Sterling our data program, Shearman Analytics, is comprised of three core pillars: Collection, Governance, and Data Analyzation. The first two pillars took the better part of two years to come to fruition and included the replacement of several core systems, policy drafting, data classification, and the creation of an overarching Master Data Management (MDM) strategy.

It is important to spend the time upfront around the creation of an MDM strategy with proper collection, governance, and data sanitization methods. It is only now in our third year of this process that we can move to the sexy stuff, the data analyzation.

The power of combined internal & external data

Leveraging internal data alone is not enough. To truly capture a holistic picture, you must gather information from external sources while blending it with your firm’s internal data. This is critical to aid in lawyers’ decision-making processes.

The ability to have external data pushed to internal applications is not new, but how it is done and the insights it derives have changed. Originally, law firms would set up federated searches within their enterprise search systems that allowed the user to cast a query and toggle between a series of tabs to see the results from each external provider.

Then about five years ago, vendors began to build out Application Programming Interfaces (APIs) to offer better indexing of such information and allow firms to begin co-mingling results. For example, an associate could perform a single search and see the results from a variety of legal research providers to which the firm had subscriptions. This provided tremendous value by giving the lawyer the best results regardless of vendor, exposing the lawyer to resources they may not have been aware, and deriving better value from firm subscriptions.

Fast forward a couple years and vendors have begun to really take development of APIs more seriously, as they see that law firms wanted to consume information differently. This change was partially driven by the advancements in technology and partially from the overall change of age demographics in lawyers that demanded pushed information vs. pulling information from multiple destinations.

At Shearman & Sterling, we have seen this shifting need for a more digital library model and delivery that goes directly into lawyers’ workflow. And the pandemic only accelerated this model as our lawyers no longer had physical access to desk books, and those previously hesitant to embrace a technology-enabled method were now forced to move online.

Proof of value

After getting our data organized, cleaned, and governed, we revamped our internal systems by working with third parties to ingest their data. Now, we were ready to move to the sexy stuff, the data analyzation. We kicked off our Litigation Proof of Value (POV) in late-summer 2020. (Note: a POV is different than a Proof of Concept (POC), as what we are looking to determine is if the lawyer is deriving value from the information, not if the software works from a technical perspective.)

Our goal was to leverage our internal data in conjunction with external data to provide easy access to our litigation experience. This would create a comprehensive snapshot of our in-court litigation experience that would allow for data-driven decision making by looking at trends in cases in which we were (and were not) involved, jurisdictional analysis, and how a judge may rule.

The scope of the POV was the last 10 years of data in state and federal courts (excluding investigations, as part of Phase 1). We started by taking cases that were in our internal docketing system and normalizing the docket numbers. We then queried vendors’ APIs to match our data, and if we didn’t match, we broadened the query by leveraging other data points to get further results. We then applied a Machine Learning algorithms to match results and merged those results with data from our Conflicts databases and Elite time and billing system on parties, timekeepers, and narratives.

Finally, we then merged with the judge list from our docketing system and pulled judicial analytics from Thomson Reuters to further enhance the data. All this data was then brought together in a single, intuitive, lawyer-friendly interface that leveraged Microsoft Power BI.


The Litigation POV is our first step into our Data Analyzation pillar of Shearman Analytics. We have plans to surface external data in conjunction with every matter, both transactional and litigation, as well as including financial data for matter pricing and profitability, in our new intranet and enterprise search systems. In order to achieve this goal, we look to partner with vendors that are forward-thinking towards APIs and allow us to access and consume data to truly provide value-add for our lawyers.

Data is our biggest asset. The more we can contextualize and provide quality data to our users in our systems, then the better decisions our lawyers can make in bringing value to our clients.

More insights