Risk analysis for intellectual property litigation

Abstract

We introduce the problem of risk analysis for Intellectual Property (IP) lawsuits. More specifically, we focus on estimating the risk for participating parties using solely prior factors, i.e., historical and concurrent behavior of the entities involved in the case. This work represents a first step towards building a comprehensive legal risk assessment system for parties involved in litigation. This technology will allow parties to optimize their case parameters to minimize their own risk, or to settle disputes out of court and thereby ease the burden on the judicial system. In addition, it will also help U.S. courts detect and fix any inherent biases in the system.We model risk estimation as a relational classification problem using conditional random fields [6] to jointly estimate the risks of concurrent cases. We evaluate our model on data collected by the Stanford Intellectual Property Litigation Clearinghouse, which consists of over 4,200 IP lawsuits filed across 88 U.S. federal districts and ranging over 8 years, probably the largest legal data set reported in data mining research. Despite being agnostic to the merits of the case, our best model achieves a classification accuracy of 64%, 22% (relative) higher than the majority-class baseline.

Identifying patent monetization entities

“…For example, Surdeanu et al forecast the outcomes of patent infringement lawsuits using solely empirical factors derived from the litigation behavior of the entities involved, such as past win rates for the parties and counsel involved [16]. Similar problems were addressed by other researchers [3,5] but, to our knowledge, this is the first work to propose an empirical model for the identification of PMEs.…”

A history of AI and Law in 50 papers: 25 years of the international conference on AI and Law

“…Many of them were published in the early to middle years of the past quarter century. By contrast, this Risk Analysis [261] paper is clearly a work that will make its impact on future research endeavors. Published in 2011, the work was circulated at a time when computational research into risk mining and risk analysis was still in its infancy.…”

“…A strength of [261] is that it defines risk in practical, legal terms -the probability of one's opponent succeeding in a legal case. Once this simple threshold is established, the authors can (and do) actively pursue models that try to use the freedom and flexibility of the features at their disposal, while admitting that they are taking small steps in framing the problem and in dealing with how much personal evidence to harness or ignore.…”

“…Given that computational Risk Analysis and Risk Mining may still be considered a fledgling field, [261] is significant as it represents an early and encouraging investigation into the prospects of using available evidence to predict key outcomes in one sub-domain of the legal field. Whether the use cases originate in Wall Street investment houses, corporate law offices, national insurance firms, or government agencies, such capabilities are clearly becoming more valued and in greater demand.…”

Intelligent trademark analysis

“…Even something as basic as a relevancy-ranked search engine for trademarks must use some model of trademark similarity in the legally relevant sense as the basis for determining the proximity of any two trademarks. In this respect trademark litigation is perhaps more straightforwardly dependent on the elements of the specific IPRs involved, as opposed to patent litigation, where the similarity aspect does not seem to play an equally crucial role [4].…”