Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Law on the Market? Abnormal Stock Returns and Supreme Court Decision-Making

Daniel Martin Katz
PRO
December 19, 2017
2.6k

Law on the Market? Abnormal Stock Returns and Supreme Court Decision-Making

What happens when the Supreme Court of the United States decides a case impacting one or more publicly-traded firms? While many have observed anecdotal evidence linking decisions or oral arguments to abnormal stock returns, few have rigorously or systematically investigated the behavior of equities around Supreme Court actions. In this research, we present the first comprehensive, longitudinal study on the topic, spanning over 15 years and hundreds of cases and firms. Using both intra- and interday data around decisions and oral arguments, we evaluate the frequency and magnitude of statistically-significant abnormal return events after Supreme Court action. On a per-term basis, we find 5.3 cases and 7.8 stocks that exhibit abnormal returns after decision. In total, across the cases we examined, we find 79 out of the 211 cases (37%) exhibit an average abnormal return of 4.4% over a two-session window with an average |t|-statistic of 2.9. Finally, we observe that abnormal returns following Supreme Court decisions materialize over the span of hours and days, not minutes, yielding strong implications for market efficiency in this context. While we cannot causally separate substantive legal impact from mere revision of beliefs, we do find strong evidence that there is indeed a "law on the market" effect as measured by the frequency of abnormal return events, and that these abnormal returns are not immediately incorporated into prices.

Daniel Martin Katz
PRO

December 19, 2017
Tweet

More Decks by Daniel Martin Katz

Transcript

  1. daniel martin katz
    michael bommarito
    tyler soellinger
    james ming chen
    Law on the Market?
    Abnormal Stock Returns
    and Supreme Court
    Decision-Making

    View Slide

  2. Law on the Market?
    Abnormal Stock Returns
    and Supreme Court
    Decision-Making
    daniel martin katz
    edu | Illinois tech - chicago kent
    blog | ComputationalLegalStudies
    corp | LexPredict.com
    tyler soellinger james ming chen
    michael bommarito
    edu | Illinois tech - chicago kent
    blog | ComputationalLegalStudies
    corp | LexPredict.com
    home | michigan state law
    corp | LexPredict.com
    home | michigan state law
    blog | jurisdynamics.blogspot.com

    View Slide

  3. Thank you very much for
    allowing us to present our work

    View Slide

  4. Thank you very much for
    allowing us to present our work

    View Slide

  5. I would like to start
    with a quick overview
    of some allied work
    before getting to the
    paper for today …
    https://papers.ssrn.com/sol3/papers.cfm?abstract_id=2649726
    Access Paper Here

    View Slide

  6. In allied work, we have
    explored judicial prediction from
    a variety of different angles …

    View Slide

  7. The Three Forms
    of (Legal) Prediction

    View Slide

  8. Experts, Crowds, Algorithms
    The Three Forms
    of (Legal) Prediction

    View Slide

  9. In so much as prediction is
    the task in question …
    #MachineLearing
    is the method du jour

    View Slide

  10. It is not necessarily ML
    alone but rather some
    ensemble of
    experts, crowds + algorithms

    View Slide

  11. http://www.sciencemag.org/news/
    2017/05/artificial-intelligence-prevails-
    predicting-supreme-court-decisions
    Professor Katz noted
    that in the long term
    …“We believe the
    blend of experts,
    crowds, and
    algorithms is the
    secret sauce for the
    whole thing.”
    May 2nd 2017

    View Slide

  12. View Slide

  13. predicting the decisions of the
    Supreme Court of the United States
    #SCOTUS

    View Slide

  14. Experts

    View Slide

  15. Columbia Law Review
    October, 2004
    Theodore W. Ruger, Pauline T. Kim,
    Andrew D. Martin, Kevin M. Quinn
    Legal and Political
    Science Approaches to
    Predicting Supreme
    Court Decision Making
    The Supreme Court
    Forecasting Project:

    View Slide

  16. experts

    View Slide

  17. Case Level Prediction
    Justice Level Prediction
    67.4% experts
    58% experts
    From the 68
    Included
    Cases
    for the
    2002-2003
    Supreme
    Court Term

    View Slide

  18. these experts probably
    overfit

    View Slide

  19. they fit to the noise
    and
    not the signal

    View Slide

  20. View Slide

  21. if this were
    finance this
    would be
    trading
    worse than
    S&P500

    View Slide

  22. #NoiseTrading

    View Slide

  23. #BuffetChallenge

    View Slide

  24. #BuffetChallenge

    View Slide

  25. like many other forms
    human endeavor
    law is full of 

    noise predictors …

    View Slide

  26. from a pure
    forecasting
    standpoint

    View Slide

  27. the best
    known
    SCOTUS
    predictor is

    View Slide

  28. View Slide

  29. the law
    version of
    superforecasting

    View Slide

  30. View Slide

  31. Crowds

    View Slide

  32. not
    enough
    crowd
    based
    decision
    making in
    institutions

    View Slide

  33. View Slide

  34. “Software developers were asked on two
    separate days to estimate the completion
    time for a given task, the hours they
    projected differed by 71%, on average.
    When pathologists made two assessments of
    the severity of biopsy results, the correlation
    between their ratings was only .61 (out of a
    perfect 1.0), indicating that they made
    inconsistent diagnoses quite frequently.
    Judgments made by different people are
    even more likely to diverge.”

    View Slide

  35. crowds

    View Slide

  36. View Slide

  37. View Slide

  38. View Slide

  39. https://fantasyscotus.lexpredict.com/case/list/
    We can
    generate
    Crowd
    Sourced
    Predictions

    View Slide

  40. not all
    members of
    crowd are
    made equal

    View Slide

  41. we maintain
    a ‘supercrowd’
    which is the top n
    of predictors
    up to time t-1
    (i.e. a Condorcet Jury)

    View Slide

  42. the ‘supercrowd’ outperforms
    the overall crowd
    (and even the best single player)

    View Slide

  43. 7000+ players
    600,000+ predictions
    From 2011-2017
    https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3085710
    Crowdsourcing Accurately
    and Robustly Predicts
    Supreme Court Decisions

    View Slide

  44. View Slide

  45. Brief Aside
    About
    Crowd
    Sourced
    Prediction
    #LegalCrowdSourcing

    View Slide

  46. (most pundits did not
    identify as a serious
    candidate him until
    mid-January 2017)
    Neil Gorsuch was #1
    o n o u r F a n t a s y
    Platform 12 Days after
    Donald Trump was
    elected President
    (i.e Nov 20)

    View Slide

  47. #FantasySCOTUS

    View Slide

  48. View Slide

  49. Algorithms

    View Slide

  50. http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0174698
    Katz DM, Bommarito MJ II, Blackman J (2017), A General
    Approach for Predicting the Behavior of the Supreme Court
    of the United States. PLoS ONE 12(4): e0174698.

    View Slide

  51. Our algorithm is a special version
    of random forest (time evolving)
    http://journals.plos.org/
    plosone/article?id=10.1371/
    journal.pone.0174698
    available at
    RESEARCH ARTICLE
    A general approach for predicting the
    behavior of the Supreme Court of the United
    States
    Daniel Martin Katz1,2*, Michael J. Bommarito II1,2, Josh Blackman3
    1 Illinois Tech - Chicago-Kent College of Law, Chicago, IL, United States of America, 2 CodeX - The Stanford
    Center for Legal Informatics, Stanford, CA, United States of America, 3 South Texas College of Law Houston,
    Houston, TX, United States of America
    * [email protected]
    Abstract
    Building on developments in machine learning and prior work in the science of judicial pre-
    diction, we construct a model designed to predict the behavior of the Supreme Court of the
    United States in a generalized, out-of-sample context. To do so, we develop a time-evolving
    random forest classifier that leverages unique feature engineering to predict more than
    240,000 justice votes and 28,000 cases outcomes over nearly two centuries (1816-2015).
    Using only data available prior to decision, our model outperforms null (baseline) models at
    both the justice and case level under both parametric and non-parametric tests. Over nearly
    two centuries, we achieve 70.2% accuracy at the case outcome level and 71.9% at the jus-
    tice vote level. More recently, over the past century, we outperform an in-sample optimized
    null model by nearly 5%. Our performance is consistent with, and improves on the general
    level of prediction demonstrated by prior work; however, our model is distinctive because it
    can be applied out-of-sample to the entire past and future of the Court, not a single term.
    Our results represent an important advance for the science of quantitative legal prediction
    and portend a range of other potential applications.
    Introduction
    As the leaves begin to fall each October, the first Monday marks the beginning of another term
    for the Supreme Court of the United States. Each term brings with it a series of challenging,
    important cases that cover legal questions as diverse as tax law, freedom of speech, patent law,
    administrative law, equal protection, and environmental law. In many instances, the Court’s
    decisions are meaningful not just for the litigants per se, but for society as a whole.
    Unsurprisingly, predicting the behavior of the Court is one of the great pastimes for legal
    and political observers. Every year, newspapers, television and radio pundits, academic jour-
    nals, law reviews, magazines, blogs, and tweets predict how the Court will rule in a particular
    case. Will the Justices vote based on the political preferences of the President who appointed
    them or form a coalition along other dimensions? Will the Court counter expectations with an
    unexpected ruling?
    PLOS ONE | https://doi.org/10.1371/journal.pone.0174698 April 12, 2017 1 / 18
    a1111111111
    a1111111111
    a1111111111
    a1111111111
    a1111111111
    OPEN ACCESS
    Citation: Katz DM, Bommarito MJ, II, Blackman J
    (2017) A general approach for predicting the
    behavior of the Supreme Court of the United
    States. PLoS ONE 12(4): e0174698. https://doi.
    org/10.1371/journal.pone.0174698
    Editor: Luı
    ´s A. Nunes Amaral, Northwestern
    University, UNITED STATES
    Received: January 17, 2017
    Accepted: March 13, 2017
    Published: April 12, 2017
    Copyright: © 2017 Katz et al. This is an open
    access article distributed under the terms of the
    Creative Commons Attribution License, which
    permits unrestricted use, distribution, and
    reproduction in any medium, provided the original
    author and source are credited.
    Data Availability Statement: Data and replication
    code are available on Github at the following URL:
    https://github.com/mjbommar/scotus-predict-v2/.
    Funding: The author(s) received no specific
    funding for this work.
    Competing interests: All Authors are Members of
    a LexPredict, LLC which provides consulting
    services to various legal industry stakeholders. We
    received no financial contributions from LexPredict
    or anyone else for this paper. This does not alter
    our adherence to PLOS ONE policies on sharing
    data and materials.

    View Slide

  52. View Slide

  53. We call this a ‘general’ model
    of #SCOTUS Prediction
    RESEARCH ARTICLE
    A general approach for predicting the
    behavior of the Supreme Court of the United
    States
    Daniel Martin Katz1,2*, Michael J. Bommarito II1,2, Josh Blackman3
    1 Illinois Tech - Chicago-Kent College of Law, Chicago, IL, United States of America, 2 CodeX - The Stanford
    Center for Legal Informatics, Stanford, CA, United States of America, 3 South Texas College of Law Houston,
    Houston, TX, United States of America
    * [email protected]
    Abstract
    Building on developments in machine learning and prior work in the science of judicial pre-
    diction, we construct a model designed to predict the behavior of the Supreme Court of the
    United States in a generalized, out-of-sample context. To do so, we develop a time-evolving
    random forest classifier that leverages unique feature engineering to predict more than
    240,000 justice votes and 28,000 cases outcomes over nearly two centuries (1816-2015).
    Using only data available prior to decision, our model outperforms null (baseline) models at
    both the justice and case level under both parametric and non-parametric tests. Over nearly
    two centuries, we achieve 70.2% accuracy at the case outcome level and 71.9% at the jus-
    tice vote level. More recently, over the past century, we outperform an in-sample optimized
    null model by nearly 5%. Our performance is consistent with, and improves on the general
    level of prediction demonstrated by prior work; however, our model is distinctive because it
    can be applied out-of-sample to the entire past and future of the Court, not a single term.
    Our results represent an important advance for the science of quantitative legal prediction
    and portend a range of other potential applications.
    Introduction
    As the leaves begin to fall each October, the first Monday marks the beginning of another term
    for the Supreme Court of the United States. Each term brings with it a series of challenging,
    important cases that cover legal questions as diverse as tax law, freedom of speech, patent law,
    administrative law, equal protection, and environmental law. In many instances, the Court’s
    decisions are meaningful not just for the litigants per se, but for society as a whole.
    Unsurprisingly, predicting the behavior of the Court is one of the great pastimes for legal
    and political observers. Every year, newspapers, television and radio pundits, academic jour-
    nals, law reviews, magazines, blogs, and tweets predict how the Court will rule in a particular
    case. Will the Justices vote based on the political preferences of the President who appointed
    them or form a coalition along other dimensions? Will the Court counter expectations with an
    unexpected ruling?
    PLOS ONE | https://doi.org/10.1371/journal.pone.0174698 April 12, 2017 1 / 18
    a1111111111
    a1111111111
    a1111111111
    a1111111111
    a1111111111
    OPEN ACCESS
    Citation: Katz DM, Bommarito MJ, II, Blackman J
    (2017) A general approach for predicting the
    behavior of the Supreme Court of the United
    States. PLoS ONE 12(4): e0174698. https://doi.
    org/10.1371/journal.pone.0174698
    Editor: Luı
    ´s A. Nunes Amaral, Northwestern
    University, UNITED STATES
    Received: January 17, 2017
    Accepted: March 13, 2017
    Published: April 12, 2017
    Copyright: © 2017 Katz et al. This is an open
    access article distributed under the terms of the
    Creative Commons Attribution License, which
    permits unrestricted use, distribution, and
    reproduction in any medium, provided the original
    author and source are credited.
    Data Availability Statement: Data and replication
    code are available on Github at the following URL:
    https://github.com/mjbommar/scotus-predict-v2/.
    Funding: The author(s) received no specific
    funding for this work.
    Competing interests: All Authors are Members of
    a LexPredict, LLC which provides consulting
    services to various legal industry stakeholders. We
    received no financial contributions from LexPredict
    or anyone else for this paper. This does not alter
    our adherence to PLOS ONE policies on sharing
    data and materials.

    View Slide

  54. Not just interested in accuracy
    over a short time window
    RESEARCH ARTICLE
    A general approach for predicting the
    behavior of the Supreme Court of the United
    States
    Daniel Martin Katz1,2*, Michael J. Bommarito II1,2, Josh Blackman3
    1 Illinois Tech - Chicago-Kent College of Law, Chicago, IL, United States of America, 2 CodeX - The Stanford
    Center for Legal Informatics, Stanford, CA, United States of America, 3 South Texas College of Law Houston,
    Houston, TX, United States of America
    * [email protected]
    Abstract
    Building on developments in machine learning and prior work in the science of judicial pre-
    diction, we construct a model designed to predict the behavior of the Supreme Court of the
    United States in a generalized, out-of-sample context. To do so, we develop a time-evolving
    random forest classifier that leverages unique feature engineering to predict more than
    240,000 justice votes and 28,000 cases outcomes over nearly two centuries (1816-2015).
    Using only data available prior to decision, our model outperforms null (baseline) models at
    both the justice and case level under both parametric and non-parametric tests. Over nearly
    two centuries, we achieve 70.2% accuracy at the case outcome level and 71.9% at the jus-
    tice vote level. More recently, over the past century, we outperform an in-sample optimized
    null model by nearly 5%. Our performance is consistent with, and improves on the general
    level of prediction demonstrated by prior work; however, our model is distinctive because it
    can be applied out-of-sample to the entire past and future of the Court, not a single term.
    Our results represent an important advance for the science of quantitative legal prediction
    and portend a range of other potential applications.
    Introduction
    As the leaves begin to fall each October, the first Monday marks the beginning of another term
    for the Supreme Court of the United States. Each term brings with it a series of challenging,
    important cases that cover legal questions as diverse as tax law, freedom of speech, patent law,
    administrative law, equal protection, and environmental law. In many instances, the Court’s
    decisions are meaningful not just for the litigants per se, but for society as a whole.
    Unsurprisingly, predicting the behavior of the Court is one of the great pastimes for legal
    and political observers. Every year, newspapers, television and radio pundits, academic jour-
    nals, law reviews, magazines, blogs, and tweets predict how the Court will rule in a particular
    case. Will the Justices vote based on the political preferences of the President who appointed
    them or form a coalition along other dimensions? Will the Court counter expectations with an
    unexpected ruling?
    PLOS ONE | https://doi.org/10.1371/journal.pone.0174698 April 12, 2017 1 / 18
    a1111111111
    a1111111111
    a1111111111
    a1111111111
    a1111111111
    OPEN ACCESS
    Citation: Katz DM, Bommarito MJ, II, Blackman J
    (2017) A general approach for predicting the
    behavior of the Supreme Court of the United
    States. PLoS ONE 12(4): e0174698. https://doi.
    org/10.1371/journal.pone.0174698
    Editor: Luı
    ´s A. Nunes Amaral, Northwestern
    University, UNITED STATES
    Received: January 17, 2017
    Accepted: March 13, 2017
    Published: April 12, 2017
    Copyright: © 2017 Katz et al. This is an open
    access article distributed under the terms of the
    Creative Commons Attribution License, which
    permits unrestricted use, distribution, and
    reproduction in any medium, provided the original
    author and source are credited.
    Data Availability Statement: Data and replication
    code are available on Github at the following URL:
    https://github.com/mjbommar/scotus-predict-v2/.
    Funding: The author(s) received no specific
    funding for this work.
    Competing interests: All Authors are Members of
    a LexPredict, LLC which provides consulting
    services to various legal industry stakeholders. We
    received no financial contributions from LexPredict
    or anyone else for this paper. This does not alter
    our adherence to PLOS ONE policies on sharing
    data and materials.

    View Slide

  55. A locally tuned model will
    typically lead to overfitting
    as the dynamics shift
    RESEARCH ARTICLE
    A general approach for predicting the
    behavior of the Supreme Court of the United
    States
    Daniel Martin Katz1,2*, Michael J. Bommarito II1,2, Josh Blackman3
    1 Illinois Tech - Chicago-Kent College of Law, Chicago, IL, United States of America, 2 CodeX - The Stanford
    Center for Legal Informatics, Stanford, CA, United States of America, 3 South Texas College of Law Houston,
    Houston, TX, United States of America
    * [email protected]
    Abstract
    Building on developments in machine learning and prior work in the science of judicial pre-
    diction, we construct a model designed to predict the behavior of the Supreme Court of the
    United States in a generalized, out-of-sample context. To do so, we develop a time-evolving
    random forest classifier that leverages unique feature engineering to predict more than
    240,000 justice votes and 28,000 cases outcomes over nearly two centuries (1816-2015).
    Using only data available prior to decision, our model outperforms null (baseline) models at
    both the justice and case level under both parametric and non-parametric tests. Over nearly
    two centuries, we achieve 70.2% accuracy at the case outcome level and 71.9% at the jus-
    tice vote level. More recently, over the past century, we outperform an in-sample optimized
    null model by nearly 5%. Our performance is consistent with, and improves on the general
    level of prediction demonstrated by prior work; however, our model is distinctive because it
    can be applied out-of-sample to the entire past and future of the Court, not a single term.
    Our results represent an important advance for the science of quantitative legal prediction
    and portend a range of other potential applications.
    Introduction
    As the leaves begin to fall each October, the first Monday marks the beginning of another term
    for the Supreme Court of the United States. Each term brings with it a series of challenging,
    important cases that cover legal questions as diverse as tax law, freedom of speech, patent law,
    administrative law, equal protection, and environmental law. In many instances, the Court’s
    decisions are meaningful not just for the litigants per se, but for society as a whole.
    Unsurprisingly, predicting the behavior of the Court is one of the great pastimes for legal
    and political observers. Every year, newspapers, television and radio pundits, academic jour-
    nals, law reviews, magazines, blogs, and tweets predict how the Court will rule in a particular
    case. Will the Justices vote based on the political preferences of the President who appointed
    them or form a coalition along other dimensions? Will the Court counter expectations with an
    unexpected ruling?
    PLOS ONE | https://doi.org/10.1371/journal.pone.0174698 April 12, 2017 1 / 18
    a1111111111
    a1111111111
    a1111111111
    a1111111111
    a1111111111
    OPEN ACCESS
    Citation: Katz DM, Bommarito MJ, II, Blackman J
    (2017) A general approach for predicting the
    behavior of the Supreme Court of the United
    States. PLoS ONE 12(4): e0174698. https://doi.
    org/10.1371/journal.pone.0174698
    Editor: Luı
    ´s A. Nunes Amaral, Northwestern
    University, UNITED STATES
    Received: January 17, 2017
    Accepted: March 13, 2017
    Published: April 12, 2017
    Copyright: © 2017 Katz et al. This is an open
    access article distributed under the terms of the
    Creative Commons Attribution License, which
    permits unrestricted use, distribution, and
    reproduction in any medium, provided the original
    author and source are credited.
    Data Availability Statement: Data and replication
    code are available on Github at the following URL:
    https://github.com/mjbommar/scotus-predict-v2/.
    Funding: The author(s) received no specific
    funding for this work.
    Competing interests: All Authors are Members of
    a LexPredict, LLC which provides consulting
    services to various legal industry stakeholders. We
    received no financial contributions from LexPredict
    or anyone else for this paper. This does not alter
    our adherence to PLOS ONE policies on sharing
    data and materials.

    View Slide

  56. We want a model that is
    robust to a large number
    of known dynamics …
    RESEARCH ARTICLE
    A general approach for predicting the
    behavior of the Supreme Court of the United
    States
    Daniel Martin Katz1,2*, Michael J. Bommarito II1,2, Josh Blackman3
    1 Illinois Tech - Chicago-Kent College of Law, Chicago, IL, United States of America, 2 CodeX - The Stanford
    Center for Legal Informatics, Stanford, CA, United States of America, 3 South Texas College of Law Houston,
    Houston, TX, United States of America
    * [email protected]
    Abstract
    Building on developments in machine learning and prior work in the science of judicial pre-
    diction, we construct a model designed to predict the behavior of the Supreme Court of the
    United States in a generalized, out-of-sample context. To do so, we develop a time-evolving
    random forest classifier that leverages unique feature engineering to predict more than
    240,000 justice votes and 28,000 cases outcomes over nearly two centuries (1816-2015).
    Using only data available prior to decision, our model outperforms null (baseline) models at
    both the justice and case level under both parametric and non-parametric tests. Over nearly
    two centuries, we achieve 70.2% accuracy at the case outcome level and 71.9% at the jus-
    tice vote level. More recently, over the past century, we outperform an in-sample optimized
    null model by nearly 5%. Our performance is consistent with, and improves on the general
    level of prediction demonstrated by prior work; however, our model is distinctive because it
    can be applied out-of-sample to the entire past and future of the Court, not a single term.
    Our results represent an important advance for the science of quantitative legal prediction
    and portend a range of other potential applications.
    Introduction
    As the leaves begin to fall each October, the first Monday marks the beginning of another term
    for the Supreme Court of the United States. Each term brings with it a series of challenging,
    important cases that cover legal questions as diverse as tax law, freedom of speech, patent law,
    administrative law, equal protection, and environmental law. In many instances, the Court’s
    decisions are meaningful not just for the litigants per se, but for society as a whole.
    Unsurprisingly, predicting the behavior of the Court is one of the great pastimes for legal
    and political observers. Every year, newspapers, television and radio pundits, academic jour-
    nals, law reviews, magazines, blogs, and tweets predict how the Court will rule in a particular
    case. Will the Justices vote based on the political preferences of the President who appointed
    them or form a coalition along other dimensions? Will the Court counter expectations with an
    unexpected ruling?
    PLOS ONE | https://doi.org/10.1371/journal.pone.0174698 April 12, 2017 1 / 18
    a1111111111
    a1111111111
    a1111111111
    a1111111111
    a1111111111
    OPEN ACCESS
    Citation: Katz DM, Bommarito MJ, II, Blackman J
    (2017) A general approach for predicting the
    behavior of the Supreme Court of the United
    States. PLoS ONE 12(4): e0174698. https://doi.
    org/10.1371/journal.pone.0174698
    Editor: Luı
    ´s A. Nunes Amaral, Northwestern
    University, UNITED STATES
    Received: January 17, 2017
    Accepted: March 13, 2017
    Published: April 12, 2017
    Copyright: © 2017 Katz et al. This is an open
    access article distributed under the terms of the
    Creative Commons Attribution License, which
    permits unrestricted use, distribution, and
    reproduction in any medium, provided the original
    author and source are credited.
    Data Availability Statement: Data and replication
    code are available on Github at the following URL:
    https://github.com/mjbommar/scotus-predict-v2/.
    Funding: The author(s) received no specific
    funding for this work.
    Competing interests: All Authors are Members of
    a LexPredict, LLC which provides consulting
    services to various legal industry stakeholders. We
    received no financial contributions from LexPredict
    or anyone else for this paper. This does not alter
    our adherence to PLOS ONE policies on sharing
    data and materials.

    View Slide

  57. 243,882
    28,009
    Case Outcomes
    Justice Votes
    Current Version of #PredictSCOTUS
    1816-2015

    View Slide

  58. Experts, Crowds, Algorithms

    View Slide

  59. expert
    forecast
    crowd
    forecast
    learning problem is to discover how to blend streams of intelligence
    algorithm
    forecast
    ensemble method
    ensemble model

    View Slide

  60. expert
    forecast
    crowd
    forecast
    learning problem is to discover how to blend streams of intelligence
    algorithm
    forecast
    ensemble method
    ensemble model
    via back testing we can learn the weights
    to apply for particular problems

    View Slide

  61. All of this is the path which
    led us to this paper …

    View Slide

  62. View Slide

  63. Law on the Market

    View Slide

  64. When we would
    present this work on
    #SCOTUS Prediction
    folks would ask us
    “why do I care about
    marginal improvements
    in prediction ? “

    View Slide

  65. Well at a very minimum — if you
    could predict the cases you could
    perhaps trade on them in the
    relevant securities market …

    View Slide

  66. In other words, given our
    ability to offer forecasts of
    judicial outcomes, we
    wondered if this information
    could inform an event
    driven trading strategy ?

    View Slide

  67. http://arxiv.org/abs/1508.05751
    available at
    http://papers.ssrn.com/sol3/papers.cfm?abstract_id=2649726

    View Slide

  68. We call this idea
    “Law on the Market”
    LOTM

    View Slide

  69. View Slide

  70. “Law on the Market”
    LOTM

    View Slide

  71. A Motivating Example
    Myriad Genetics
    NASDAQ: MYGN
    Market Cap of ~$3 billion+

    View Slide

  72. Myraid Genetics
    “Myriad employs a number of proprietary
    technologies that permit doctors and patients
    to understand the genetic basis of human
    disease and the role that genes play in the
    onset, progression and treatment of disease.”

    View Slide

  73. Myraid Genetics
    “Myriad was the subject of scrutiny
    after it became involved in a lengthy
    lawsuit over its controversial patenting
    practices” which including the
    patenting of human gene sequences ....

    View Slide

  74. View Slide

  75. June 13, 2013
    Supreme Court
    Offers this
    Decision
    ~10:05am

    View Slide

  76. Initial Media
    Reports and
    Initial Trading
    11:48am

    View Slide

  77. Initial Media
    Reports
    Early
    Afternoon
    “In early afternoon trading
    Thursday, Myriad shares
    were up 5.4 percent, or
    $2.36, at $35.73.”

    View Slide

  78. Final Media
    Reports

    View Slide

  79. Final Media
    Reports

    View Slide

  80. 9:30am
    Open

    View Slide

  81. 10:00am
    SCOTUS

    View Slide

  82. 11:05am
    MYGN Trades UP

    View Slide

  83. 2:15pm
    MYGN is Off its
    Daily Peak but still up

    View Slide

  84. Day 1 Close
    MYGN
    is Off Nearly 10% from Open
    and 20% from Daily High

    View Slide

  85. Day 2 the Sell Off Continues

    View Slide

  86. A Good Time to Buy an Option :)

    View Slide

  87. View Slide

  88. View Slide

  89. So these examples
    represent a form of
    existence proof …

    View Slide

  90. But perhaps they are rare
    and anachronistic cases …?

    View Slide

  91. View Slide

  92. One obvious challenge is the
    prospect that this information is
    already incorporated into the
    price of the relevant security
    #EfficientMarketHypothesis
    #Fama #EMH

    View Slide

  93. In allied fields of human endeavor, there
    are fairly rapid market responses to
    changes in the information environment

    View Slide

  94. This all presupposes a rigorous
    information and modeling environment
    — that is historically lacking for
    questions of legal prediction
    #QuantitativeLegalPrediction
    #LegalAnalytics #FinLegalTech

    View Slide

  95. View Slide

  96. Theoretical +
    Empirical Questions

    View Slide

  97. Market Incorporation Hypothesis
    Are judicial decisions already
    reflected in the share price ?
    (If this were true - we would rarely
    see market move post decision)

    View Slide

  98. How General Are
    These Specific Examples?
    Theoretical + Empirical Questions
    (In other words, is this a general phenomenon ?)

    View Slide

  99. What is the nature of the signal
    incorporation environment ?
    (In other words, what are the dynamics
    associated with does the market response ?)
    Theoretical + Empirical Questions

    View Slide

  100. View Slide

  101. Methods

    View Slide

  102. (1) Coding / PreProcessing
    (2) Candidate LOTM Events
    (3) Formal Evaluation Using
    CAPM (market model of returns)
    (4) Evaluate Speed of Incorporation
    and Related Informational Dynamics

    View Slide

  103. (1) Coding / PreProcessing
    We reviewed and coded 1,363 total
    cases decided over the period in
    questions.
    We asked a simple question - could
    this case plausibly impact a publicly
    traded security ?

    View Slide

  104. 1,363 total cases reviewed in our
    sample, we identified 211 candidate
    LOTM cases plausibly affecting one
    or more firms or sectors.
    (these included parties to the case but also third parties)
    (2) Candidate LOTM Events

    View Slide

  105. All Data &
    Code is
    Available
    Here^
    ^Other than the WRDS Data
    which is *not* open source but
    can be obtained from Wharton
    https://github.com/mjbommar/law-on-the-market
    https://wrds-web.wharton.upenn.edu/wrds/

    View Slide

  106. (3) Formal Evaluation Using
    CAPM (market model of returns)

    View Slide

  107. Abnormal
    Returns
    Common approach is
    to use index as baseline
    and seek to identify
    statistically significant
    deviations from that
    baseline
    We want to isolate the
    effect of the event from
    other general market
    movements

    View Slide

  108. Formalization
    of
    CAPM in
    Appendix A

    View Slide

  109. Formalization
    of
    CAPM in
    Appendix A

    View Slide

  110. Formalization
    of
    CAPM in
    Appendix A

    View Slide

  111. Implementation
    ‘erer’

    View Slide

  112. From a methods standpoint,
    our approach is to estimation
    is extremely standard
    (The Higher Frequency data is the
    interesting part of the paper)

    View Slide

  113. Interday studies, however, face a difficult
    and unavoidable tradeoff: either a
    researcher must rely upon relatively few
    data points, or they must collect data
    over longer durations in order to
    generate a sufficient statistical sample.
    Nearly every event study in law,and the
    vast majority of analysis in finance,
    leverages data with at most daily
    frequency.

    View Slide

  114. This Paper Leverages 5 Minute Data
    -5 Days, +5 Days
    much higher frequency than
    most papers in literature

    View Slide

  115. SOME
    RESULTS

    View Slide

  116. Summary
    Results

    View Slide

  117. Market
    Cap

    View Slide

  118. Some
    Additional
    Cases

    View Slide

  119. (4) Evaluate Speed of Incorporation
    and Related Informational Dynamics

    View Slide

  120. Speed
    of
    Information
    Incorporation

    View Slide

  121. This is very
    slow …
    Perhaps the
    real action is
    in the options
    market ?

    View Slide

  122. Relationship Between
    Oral Argument and Decision

    View Slide

  123. (1) We follow the convention (Fama French) and use log returns
    (2) If you believe in Fama French than we give you the Pearson
    but we also show the non-parametric as well (aka Spearman)
    (3) Pearson and Spearman offer a similar story

    View Slide

  124. No Clear Directional Effect
    Some Level of is
    magnitude / volatility
    based impact

    View Slide

  125. Yet only as a precursor to future movement (volatility)
    but not the direction of that future movement
    Oral argument appears to update the information space
    From a trading standpoint, this counsels a volatility
    straddle but the case for more direct options is less clear

    View Slide

  126. In conclusion, we believe that
    this research raises many
    questions and justifies a range
    of future work in the area

    View Slide

  127. Future Work
    Real Trading Strategy Analysis
    Other Classes of Litigation Events
    8k’s and Docket Arbitrage
    Higher and Lower Order Analysis
    Litigation Reserves, etc.

    View Slide

  128. Real Trading Strategy Analysis
    Not Enough to be Able to Predict …
    Need to track real or synthetic trades

    View Slide

  129. Other Classes of Litigation Events
    8k’s and Docket Arbitrage

    View Slide

  130. Litigation Funding

    View Slide

  131. Other Classes of Litigation Events
    Litigation Funding and Reserves
    Litigation
    Reserves

    View Slide

  132. Law on the Market?
    Abnormal Stock Returns
    and Supreme Court
    Decision-Making
    daniel martin katz
    edu | Illinois tech - chicago kent
    blog | ComputationalLegalStudies
    corp | LexPredict.com
    tyler soellinger james ming chen
    michael bommarito
    edu | Illinois tech - chicago kent
    blog | ComputationalLegalStudies
    corp | LexPredict.com
    home | michigan state law
    corp | LexPredict.com
    home | michigan state law
    blog | jurisdynamics.blogspot.com

    View Slide