Data Science for

the Legal
Profession

With the increase of data that is

produced and with no sign of
slowing down any time soon,
coupled with advancements in
machine hardware the legal
profession is set for a major data
driven overhaul in the coming
years.
Disclaimer

The material in this document is intended for information purposes only and should not be taken as
a commitment to deliver any product or service, and may not be incorporated into any contract.
Contents
Summary ................................................................................................................................................. 3
Data Science and the Legal Profession ................................................................................................... 4
Big Data ................................................................................................................................................... 5
Machine Learning.................................................................................................................................... 6
Predictive Analytics ................................................................................................................................. 7
Emerging Applications of Data Science for the Legal Profession. .......................................................... 8
Case Assessment and Prediction ........................................................................................................ 8
Discovery ............................................................................................................................................. 9
Judge Analysis ................................................................................................................................... 10
Opposition Scrutiny........................................................................................................................... 11
Client and Witness Insights ............................................................................................................... 12
Case Strategy Development .............................................................................................................. 13
Conclusion ............................................................................................................................................. 14

Page|2
 Summary

This white paper presents an overview of how this document we discuss where these
Data Science related technologies are growing technologies may take the legal profession in
in the legal profession. The paper also the future and the importance of embracing
highlights where Quanovo believes the main the technology early to gain competitive
areas are that legal companies can use these advantage.
technologies to their advantage if they are not
already doing so. Finally, in the conclusion of
Page|3
Data Science and the Legal Profession

Traditionally the legal profession has a fairly such systems is greater in the USA but the UK
conservative outlook when it comes to and the rest of Europe are not far behind with
adopting new technology and integrating it traditional systems being overhauled and
successfully into their businesses. However, government initiatives being put in place to
the last decade has seen a major shift in the aid with the provision of open data. All of this
way data is produced and more importantly provides a solid platform for Data Science and
how it is accessible. Big Data has become its related technologies to really take off in
more powerful as a result and has been the legal profession in the coming years.
utilised across most industries, including
Legal profession clients are no longer willing
government and healthcare, in order to
to pay the huge hourly fees that they were
achieve desired outcomes. Legal professionals
used to a decade ago. A large part of that
have been using hidden facts found in court
hourly fee is made up from the teams of
documents such as witness statements,
associates and paralegals that work on each
judge’s summaries and court logs to help
case. With the help of digital solutions law
them win arguments but, like those other
firms are able to cut down on their overheads
industries, the legal system is creating an
per case by employing less people to do the
ever-increasing amount of data. That is where
same amount of work through a symbiotic
Data Science and technologies such as
working relationship with machines. Not only
Machine Learning and Big Data analytics can
does this solution help keep costs down but in
help. They are able to deal with the volume of
many circumstances, it can actually mean
data that is produced and return actionable
finding the right information a lot faster that
results in real time meaning that legal
previously possible.
professionals are able to concentrate more on
task that require a human touch rather than In this document, we will explore some of the
the grind of fact gathering and analysis. ways that Data Science can be utilised
effectively in the new data powered
Case information is becoming more and more
landscape that is emerging in the legal
accessible with online resources storing huge
profession.
amounts of digital documents that in many
cases can be accessed for free. The delivery of
Page|4
 Big Data

Big Data is not a new phenomenon, in fact the notion has been around for almost half a century.
However, it is a topic that has been growing in exposure across every industry in recent years. There
are two main reasons that, although the idea of Big Data has been around for some time, it is now
gaining traction and rapidly:

 The first of these two reasons are that globally we are producing greater quantities of data
than ever before meaning that how we store and process that data to make constructive use
of it has become a key issue.
 The second reason is that the advancement of hardware solutions has reached the point
where they are capable of running hat the underlying algorithms on such huge data sets.
Meaning that no longer is the field of Big Data confined to a corner of academia or indeed
gigantic organisations as the hardware required has become more affordable and practical
to obtain and use.

Interest over time - Big Data 1

100

90

80

70
Interest Percentage

60

50

40

30

20

10

0
2012 2013 2014 2015 2016
Year
Page|5

1
Data from Google Trends - https://www.google.com/trends/explore?q=big%20data
Machine Learning

Machine Learning is similar to the process of Data Mining and in many ways, can be considered a
subset of the field. Both share the concept of looking through data with the goal of identifying
patterns and establishing connections.

The algorithms that Machine Learning is built upon can be very useful for extracting qualitative data
from datasets that are simply too large for people to sort through. These algorithms are generally
split into two main categories, supervised and unsupervised. Supervised Machine Learning
algorithms take what has already been learned and apply that knowledge to new data, whereas
Unsupervised Machine Learning is the process of sifting through data with the aim of discovering
some, as yet unknown meaning, from it.

In the real world, what this means is that we can utilise Machine Leaning technology to carry out
tasks such as extract sentiment from bodies of text like product reviews and use that information to
derive the reasons for negative or positive feedback.

The real power of Machine Learning comes from the fact that it is a technology that can enable the
prediction of future events even when certain datasets are absent.

Interest over time - Machine Learning 2

100

90

80

70
Interest Percentage

60

50

40

30

20

10

0
2012 2013 2014 2015 2016
Year
Page|6

2
Data from Google Trends - https://trends.google.com/trends/explore?q=machine%20learning
 Predictive Analytics

When applied in the realm of Machine Learning the term Predictive Analytics refers to the ability to
predict future outcomes using trends and indications that can be derived from the underlying data.
By predicting what is likely to occur in the future, Predictive Analytics provide the opportunity for an
organisation to gain advantage surrounding any action that should be taken and in doing so
transitions that business from reactive to proactive.

The direct applications of Predictive Analytics to the legal profession may take the form of answering
questions such as how a specific judge is likely to react to particular legal argument? Or what are the
current trends for win/loss rates for a specific type of case? That last one could also lead to
Prescriptive Analytical insight in helping to answer the question of What a good case framework
might be to follow for that case to maximise chances of a win?

Interest over time - Predictive Analytics

100

90

80

70
Interest Percentage

60

50

40

30

20

10

0
2012 2013 2014 2015 2016
Year
Page|7
 Emerging Applications of Data Science
for the Legal Profession.

A huge misconception when it comes to Machine Learning is

that, in order to produce any useful insights, an organisation
must have huge amounts of data. It is not quite as black and
“Advise on how a white as this and in fact many legal firms already have
adequate volumes and quality of data to begin exploring the
particular type of Data Science techniques available to them.
case will fare under
certain
Case Assessment and Prediction
circumstances.”
More and more, law firms are turning to Big Data to identify
which cases are likely to be straight forward and which cases
will have hidden hurdles to overcome. The basis of a good
lawyer comes not just from their understanding of the law but
also from the experience they have navigating its countless
nuances and dealing with the numerous moving parts that
make up the legal profession. Once a lawyer has that
experience they become extremely valuable to a law firm in
being able to advise on how a particular type of case will fare
under certain circumstances. This sort of insight is invaluable
but it takes many years to obtain and also usually is only
focused on one area of the law as lawyers tend to specialise as
they progress through their careers. Through the power of
Data Science technologies, it is possible to analyse the large
amounts of case data that is available both publicly and
internally to provide similar insights for every lawyer at the
company.

The types of insight that can be produced are determined by

the data that is available but can range from providing insight
into potential case outcomes based on input parameters to
assessing litigation cases with regards to a patent history.
Page|8
 Discovery

One of the biggest areas that Data Science can impact the legal
profession is through intelligent software providing electronic
discovery solutions. Many organisations often store hundreds
of thousands, if not millions, of documents in electronic
formats. The main reason they do this is for regulatory
purposes, but this can mean that for a law firm they will need “Automatically
to deploy many hours painstakingly sifting through all of that
data. However, through semantic analysis and predictive
present key
solutions it is possible for a machine to handle the grunt work information from
that goes into this stage of discovery. This can be a huge boost
related cases and
to a law firm as not only does it free up associates and
paralegals for other tasks but it can also be done in a smaller cite instances of
time frame meaning you get more time to prepare your case. similar cases or
With Data Science techniques, this type of automation can be rulings in the past."
taken a step further. Through the analysis of the correct types
of data it is possible for a system to automatically present key
information from related cases and citing instances of similar
cases or rulings in the past. Packaged all together with natural
language processing this type of solution can become an
invaluable source of research to any law firm.
Page|9
 Judge Analysis

We all know that judges are supposed to be impartial, and to

the extent they can be most of them are. However, the law is
all about interpretation and as not everyone is the same it is
inevitable that one judge may interpret something different
from another. Through the correct analysis of legal
“Highlight relevant documents, it is possible to identify hidden patterns that
would not have otherwise be visible.
arguments that
This method of analytics can provide valuable insight into how
have previously
to craft legal arguments in a way that might be better received
resonated well with by one judge over another. Predictive analytic techniques can
that judge.” be deployed here to aid with specific phrasing and can even
highlight relevant arguments that have previously resonated
well with that judge in similar cases previously.

Over time it is likely that as more law firms gain access to this
type of awareness it will put pressure on judges to be more
consistent in their rulings. This in turn will both strengthen this
type of system but also mean that incorrect rulings will
become less frequent.

Page|10
 Opposition Scrutiny

When planning a strategy for a case it helps if you can

understand the opposing lawyer and their company.
Understanding how they think and what arguments they are
likely to use can give a huge advantage. There is a greater
number of open data sources that contain case logs and other
legal documentation relating to cases that can be harvested “Build a profile of
and used in conjunction with Data Science to provide this level
of insight into your opposition. your opposition
Previously a law firm would conduct opposition research
that can be
manually, paying out huge amounts for the hours they spent consulted
pouring over pervious case files looking for relevant
throughout the
information. Using a Data Science enabled solution it is
possible to build a profile of your opposition that can be case.”
consulted throughout the case. As well as instant access, not
just to their previous cases but to the relevant sections of
those cases as well through the power of Natural Language
Processing.
Page|11
 Client and Witness Insights

The term Big Data is often confused as simply referring to the

volume of data. In fact, just as much emphasis should be
placed on the variety of that data as well. Every document,
photograph, video and social media post is a source of data
that can be analysed and turned into useful information.
“Emphasis should Accessing this data can be a useful way for a legal team to
build up a clear picture of a client or a potential witness. This
be placed on the type of information can then be used to indicate any potential
variety of data.” areas of concern or advantage that might be exploited during
the case in your favour.

Harvesting such data is not as out of reach as it may sound. In

reality a law firm could have its own software solution that
acquires the relevant data and then automatically links the
necessary information insights to the relevant cases.

Page|12
 Case Strategy Development

Legal proceedings often generate a lot of documents and if

analysed properly the statistical data that they provide can be
extremely valuable. Data Science can enable law firms to easily
examine large amounts of information to find underlying
patterns that could not previously be identified by humans
alone. Every new case adds mountains of documents that can “More than simply
take a large proportion of a lawyer’s time to sift through for
each case. This whole process can be streamlined through the streamlining the
use of machines to present lawyers with a condensed set of process Data
relevant facts and data relating to their current case. This in
turn allows the lawyers more time to understand how to use Science can provide
the material effectively. actionable
More than simply streamlining the process Data Science can prescriptive
provide actionable prescriptive analytics as well. With the right
tools, it is possible to take the patterns and connections from
analytics as well.”
thousands or more legal precedents and suggest important
strategies that may have been missed through traditional case
research. Advice on the way an argument should be crafted
depending on the type of case, the presiding judge, the
opposing law firm and many other factors can be invaluable,
especially to a firm wishing to reduce its overheads without
sacrificing quality.
Page|13
Conclusion

With the increase of data that is produced and with no sign of slowing down any time soon, coupled
with advancements in machine hardware the legal profession is set for a major data driven overhaul
in the coming years. Data Science offers opourtunities to increase efficiency and reduce costs as well
as allowing greater transparency across the judicial system. The only obstacle to these advantages is
the legal profession itself with change not always quick to be adopted.

There are those that fear the loss of jobs due to automation, however for at least the short to mid-
term the likelihood of such systems replacing lawyers is far from a reality. However, that does not
mean that jobs in the legal profession are not about to change. Previously skills surrounding basic
legal research were a large part of a lawyer or paralegal’s job. However, with new technology being
applied in the legal profession there will be an increased need for legal experts with data literacy
skills as well.

We are not currently at this point yet however and with law firms being slow to adopt this
technology it is likely that those who do so first will reap the greatest rewards, being able to offer
better pricing without compromising service. It is also likely that those who make the shift to data
driven services first will be better placed to take advantage of new technologies in the Data Science
space as they are developed.

Such combinations between lawyers and machine learning, data and analytics provide a powerful
mix that can enable legal firms to better and more efficiently serve their clients while also finding
ways to separate themselves from competitors and do a better job of retaining clients and bringing
in new ones.

Page|14