Predicting litigation likelihood and time to litigation for patents

P. Wongchaisuwat, Diego Klabjan, John O McGinnis

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

An ability to forecast the likelihood of a patent litigation1 and time-to-litigation benets companies in many aspects, such as in patent portfolio management, and strategic planning. Thus, we develop predictive models for estimating the likelihood of litigation for patents and the expected time to litigation. Our work focuses on improving the state-of-the-art by relying on a dierent set of features and employing more sophisticated algorithms with realistic data. Specically, we consider potential factors inuencing a patent to be litigated in the model. These features, collected at the issue date of the patent and thus prior to the actual litigation, include textual features, patent’s general information as well as nancial information of patent’s assignee. Our proposed models are a combination of a clustering approach coupled with an ensemble classication method. With a very low litigation rate of 1 to 2 percent, the results from the models show promising predictability. Financial information and features related to referencing are important indicators to distinguish between litigated and non-litigated patents.

Original languageEnglish (US)
Title of host publicationProceedings of the 16th International Conference on Artificial Intelligence and Law, ICAIL 2017
PublisherAssociation for Computing Machinery
Pages257-260
Number of pages4
ISBN (Electronic)9781450348911
DOIs
StatePublished - Jun 12 2017
Event16th International Conference on Artificial Intelligence and Law, ICAIL 2017 - London, United Kingdom
Duration: Jun 12 2017Jun 16 2017

Publication series

NameProceedings of the International Conference on Artificial Intelligence and Law

Other

Other16th International Conference on Artificial Intelligence and Law, ICAIL 2017
CountryUnited Kingdom
CityLondon
Period6/12/176/16/17

Fingerprint

patent
Strategic planning
portfolio management
management planning
time
predictive model
strategic planning
Industry
ability

Keywords

  • Anomaly detection
  • Classication
  • Machine learning
  • Patent litigation

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence
  • Law

Cite this

Wongchaisuwat, P., Klabjan, D., & McGinnis, J. O. (2017). Predicting litigation likelihood and time to litigation for patents. In Proceedings of the 16th International Conference on Artificial Intelligence and Law, ICAIL 2017 (pp. 257-260). (Proceedings of the International Conference on Artificial Intelligence and Law). Association for Computing Machinery. https://doi.org/10.1145/3086512.3086545
Wongchaisuwat, P. ; Klabjan, Diego ; McGinnis, John O. / Predicting litigation likelihood and time to litigation for patents. Proceedings of the 16th International Conference on Artificial Intelligence and Law, ICAIL 2017. Association for Computing Machinery, 2017. pp. 257-260 (Proceedings of the International Conference on Artificial Intelligence and Law).
@inproceedings{fec4c6c6a60f419fb384c0dfd73b64b8,
title = "Predicting litigation likelihood and time to litigation for patents",
abstract = "An ability to forecast the likelihood of a patent litigation1 and time-to-litigation benets companies in many aspects, such as in patent portfolio management, and strategic planning. Thus, we develop predictive models for estimating the likelihood of litigation for patents and the expected time to litigation. Our work focuses on improving the state-of-the-art by relying on a dierent set of features and employing more sophisticated algorithms with realistic data. Specically, we consider potential factors inuencing a patent to be litigated in the model. These features, collected at the issue date of the patent and thus prior to the actual litigation, include textual features, patent’s general information as well as nancial information of patent’s assignee. Our proposed models are a combination of a clustering approach coupled with an ensemble classication method. With a very low litigation rate of 1 to 2 percent, the results from the models show promising predictability. Financial information and features related to referencing are important indicators to distinguish between litigated and non-litigated patents.",
keywords = "Anomaly detection, Classication, Machine learning, Patent litigation",
author = "P. Wongchaisuwat and Diego Klabjan and McGinnis, {John O}",
year = "2017",
month = "6",
day = "12",
doi = "10.1145/3086512.3086545",
language = "English (US)",
series = "Proceedings of the International Conference on Artificial Intelligence and Law",
publisher = "Association for Computing Machinery",
pages = "257--260",
booktitle = "Proceedings of the 16th International Conference on Artificial Intelligence and Law, ICAIL 2017",

}

Wongchaisuwat, P, Klabjan, D & McGinnis, JO 2017, Predicting litigation likelihood and time to litigation for patents. in Proceedings of the 16th International Conference on Artificial Intelligence and Law, ICAIL 2017. Proceedings of the International Conference on Artificial Intelligence and Law, Association for Computing Machinery, pp. 257-260, 16th International Conference on Artificial Intelligence and Law, ICAIL 2017, London, United Kingdom, 6/12/17. https://doi.org/10.1145/3086512.3086545

Predicting litigation likelihood and time to litigation for patents. / Wongchaisuwat, P.; Klabjan, Diego; McGinnis, John O.

Proceedings of the 16th International Conference on Artificial Intelligence and Law, ICAIL 2017. Association for Computing Machinery, 2017. p. 257-260 (Proceedings of the International Conference on Artificial Intelligence and Law).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Predicting litigation likelihood and time to litigation for patents

AU - Wongchaisuwat, P.

AU - Klabjan, Diego

AU - McGinnis, John O

PY - 2017/6/12

Y1 - 2017/6/12

N2 - An ability to forecast the likelihood of a patent litigation1 and time-to-litigation benets companies in many aspects, such as in patent portfolio management, and strategic planning. Thus, we develop predictive models for estimating the likelihood of litigation for patents and the expected time to litigation. Our work focuses on improving the state-of-the-art by relying on a dierent set of features and employing more sophisticated algorithms with realistic data. Specically, we consider potential factors inuencing a patent to be litigated in the model. These features, collected at the issue date of the patent and thus prior to the actual litigation, include textual features, patent’s general information as well as nancial information of patent’s assignee. Our proposed models are a combination of a clustering approach coupled with an ensemble classication method. With a very low litigation rate of 1 to 2 percent, the results from the models show promising predictability. Financial information and features related to referencing are important indicators to distinguish between litigated and non-litigated patents.

AB - An ability to forecast the likelihood of a patent litigation1 and time-to-litigation benets companies in many aspects, such as in patent portfolio management, and strategic planning. Thus, we develop predictive models for estimating the likelihood of litigation for patents and the expected time to litigation. Our work focuses on improving the state-of-the-art by relying on a dierent set of features and employing more sophisticated algorithms with realistic data. Specically, we consider potential factors inuencing a patent to be litigated in the model. These features, collected at the issue date of the patent and thus prior to the actual litigation, include textual features, patent’s general information as well as nancial information of patent’s assignee. Our proposed models are a combination of a clustering approach coupled with an ensemble classication method. With a very low litigation rate of 1 to 2 percent, the results from the models show promising predictability. Financial information and features related to referencing are important indicators to distinguish between litigated and non-litigated patents.

KW - Anomaly detection

KW - Classication

KW - Machine learning

KW - Patent litigation

UR - http://www.scopus.com/inward/record.url?scp=85045929328&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045929328&partnerID=8YFLogxK

U2 - 10.1145/3086512.3086545

DO - 10.1145/3086512.3086545

M3 - Conference contribution

AN - SCOPUS:85045929328

T3 - Proceedings of the International Conference on Artificial Intelligence and Law

SP - 257

EP - 260

BT - Proceedings of the 16th International Conference on Artificial Intelligence and Law, ICAIL 2017

PB - Association for Computing Machinery

ER -

Wongchaisuwat P, Klabjan D, McGinnis JO. Predicting litigation likelihood and time to litigation for patents. In Proceedings of the 16th International Conference on Artificial Intelligence and Law, ICAIL 2017. Association for Computing Machinery. 2017. p. 257-260. (Proceedings of the International Conference on Artificial Intelligence and Law). https://doi.org/10.1145/3086512.3086545