ARCHIVED CONTENT
You are viewing ARCHIVED CONTENT released online between 1 April 2010 and 24 August 2018 or content that has been selectively archived and is no longer active. Content in this archive is NOT UPDATED, and links may not function.
 

Predictive Coding One-Question Provider Implementation Survey – Initial Results

Provided below for your consideration and use are the in-progress results of the One-Question Provider Implementation Survey launched by ComplexDiscovery on 3/3/13.

The goal of the survey is to provide a specific and detailed look at the use of the technology-assisted review feature of predictive coding among leading eDiscovery providers as represented by those providers. The specific technologies highlighted in the one-question survey include:

  • Active Learning
  • Language Modeling
  • Latent Semantic Analysis
  • Linguistic Analysis
  • Naive Bayesian Classifier
  • Nearest Neighbor Classifier
  • Probabilistic Latent Semantic Analysis
  • Relevance Feedback
  • Support Vector Machine
  • Other (Provider Machine Learning Approach Not Listed)

The in-progress results consist of survey answers harvested directly from the online survey form as completed by provider representatives. Additional survey responses from the eDiscovery provider community will be added to this listing as they are completed.

Additional responders are welcome and encouraged. Click here to go to survey.

Note: The running results of a previously presented general survey on eDiscovery provider use of predictive coding are available for review(2) (click here for survey results).  The initial 120-second survey(3) (click here for initial survey form) contained six high level questions related to technology development, offering integration, machine learning approach and sampling approach of providers in relation to predictive coding.  The following one-question provider implementation survey was designed to build on the machine learning question from the initial general survey by providing additional and important layers of detail.

Updated 9/16/2013

Current Responders

  • @Legal
  • Altep
  • BIA
  • Catalyst Repository Systems
  • Content Analyst
  • D4
  • Daegis
  • Driven
  • Huron Legal
  • kCura
  • Kroll Ontrack
  • Liquid Litigation Management (LLM)
  • Nuix
  • Orange Legal Technologies
  • OrcaTec
  • Prolorem
  • Recommind
  • Servient
  • Symantec/Clearwell
  • TCDI
  • UBIC
  • Valora Technologies
  • Xerox Litigation Services

Current Responses (By Provider)

@Legal (CasePoint TAR) @AtLegal

  • Nearest Neighbor Classifier:  A classification system that categorizes documents by finding an already classified example that is very similar (near) to the document being considered. It gives the new document the same category as the most similar trained example.
  • Support Vector Machine:  A mathematical approach that seeks to find a line that separates responsive from non-responsive documents so that, ideally, all of the responsive documents are on one side of the line and all of the non-responsive ones are on the other side.

Altep (Tag | Content Analyst) @Altep_Inc

  • Active Learning: An iterative process that presents for reviewer judgment those documents that are most likely to be misclassified.  In conjunction with Support Vector Machines, it presents those documents that are closest to the current position of the separating line.  The line is moved if any of the presented documents has been misclassified.
  • Latent Semantic Analysis:  A mathematical approach that seeks to summarize the meaning of words by looking at the documents that share those words.  LSA builds up a mathematical model of how words are related to documents and lets users take advantage of these computed relations to categorize documents.

BIA (BIA Predictive Coding Engine | Coda™) @BIA_eDiscovery

  • Active Learning: An iterative process that presents for reviewer judgment those documents that are most likely to be misclassified.  In conjunction with Support Vector Machines, it presents those documents that are closest to the current position of the separating line.  The line is moved if any of the presented documents has been misclassified.
  • Language Modeling:  A mathematical approach that seeks to summarize the meaning of words by looking at how they are used in the set of documents.  Language modeling in predictive coding builds a model for word occurrence in the responsive and in the non-responsive documents and classifies documents according to the model that best accounts for the words in a document being considered.
  • Latent Semantic Analysis:  A mathematical approach that seeks to summarize the meaning of words by looking at the documents that share those words.  LSA builds up a mathematical model of how words are related to documents and lets users take advantage of these computed relations to categorize documents.
  • Linguistic Analysis:  Linguists examine responsive and non-responsive documents to derive classification rules that maximize the correct classification of documents.
  • Naïve Bayesian Classifier:  A system that examines the probability that each word in a new document came from the word distribution derived from trained responsive document or from trained non-responsive documents.  The system is naïve in the sense that it assumes that all words are independent of one another.
  • Nearest Neighbor Classifier:  A classification system that categorizes documents by finding an already classified example that is very similar (near) to the document being considered. It gives the new document the same category as the most similar trained example.
  • Probabilistic Latent Semantic Analysis:  A second mathematical approach that seeks to summarize the meaning of words by looking at the documents that share those words.  PLSA builds up a mathematical model of how words are related to documents and lets users take advantage of these computed relations to categorize documents.
  • Relevance Feedback:  A computational model that adjusts the criteria for implicitly identifying responsive documents following feedback by a knowledgeable user as to which documents are relevant and which are not.
  • Support Vector Machine:  A mathematical approach that seeks to find a line that separates responsive from non-responsive documents so that, ideally, all of the responsive documents are on one side of the line and all of the non-responsive ones are on the other side.

Catalyst Repository Systems (Insight Predict) @CatalystSecure

  • Nearest Neighbor Classifier:  A classification system that categorizes documents by finding an already classified example that is very similar (near) to the document being considered. It gives the new document the same category as the most similar trained example.

Content Analyst (Conceptual Categorization) @Content_Analyst

  • Active Learning: An iterative process that presents for reviewer judgment those documents that are most likely to be misclassified.  In conjunction with Support Vector Machines, it presents those documents that are closest to the current position of the separating line.  The line is moved if any of the presented documents has been misclassified.
  • Latent Semantic Analysis:  A mathematical approach that seeks to summarize the meaning of words by looking at the documents that share those words.  LSA builds up a mathematical model of how words are related to documents and lets users take advantage of these computed relations to categorize documents.

D4 Discovery (Equivio Relevance) @D4Discovery

  • Active Learning: An iterative process that presents for reviewer judgment those documents that are most likely to be misclassified.  In conjunction with Support Vector Machines, it presents those documents that are closest to the current position of the separating line.  The line is moved if any of the presented documents has been misclassified.
  • Support Vector Machine:  A mathematical approach that seeks to find a line that separates responsive from non-responsive documents so that, ideally, all of the responsive documents are on one side of the line and all of the non-responsive ones are on the other side.

Daegis (Acumen) @Daegis

  • Active Learning: An iterative process that presents for reviewer judgment those documents that are most likely to be misclassified.  In conjunction with Support Vector Machines, it presents those documents that are closest to the current position of the separating line.  The line is moved if any of the presented documents has been misclassified.
  • Probabilistic Latent Semantic Analysis:  A second mathematical approach that seeks to summarize the meaning of words by looking at the documents that share those words.  PLSA builds up a mathematical model of how words are related to documents and lets users take advantage of these computed relations to categorize documents.

Driven (START (Simplified Technology Assisted Review Tool)) (Content Analyst)

  • Active Learning: An iterative process that presents for reviewer judgment those documents that are most likely to be misclassified.  In conjunction with Support Vector Machines, it presents those documents that are closest to the current position of the separating line.  The line is moved if any of the presented documents has been misclassified.
  • Latent Semantic Analysis:  A mathematical approach that seeks to summarize the meaning of words by looking at the documents that share those words.  LSA builds up a mathematical model of how words are related to documents and lets users take advantage of these computed relations to categorize documents.
  • Nearest Neighbor Classifier:  A classification system that categorizes documents by finding an already classified example that is very similar (near) to the document being considered. It gives the new document the same category as the most similar trained example.
  • Relevance Feedback:  A computational model that adjusts the criteria for implicitly identifying responsive documents following feedback by a knowledgeable user as to which documents are relevant and which are not.

Huron Legal (Integrated Analytics | PureDiscovery) @HuronLegal

  • Nearest Neighbor Classifier:  A classification system that categorizes documents by finding an already classified example that is very similar (near) to the document being considered. It gives the new document the same category as the most similar trained example.

kCura (Relativity Assisted Review | Content Analyst)

  • Latent Semantic Analysis:  A mathematical approach that seeks to summarize the meaning of words by looking at the documents that share those words.  LSA builds up a mathematical model of how words are related to documents and lets users take advantage of these computed relations to categorize documents.
  • Nearest Neighbor Classifier:  A classification system that categorizes documents by finding an already classified example that is very similar (near) to the document being considered. It gives the new document the same category as the most similar trained example.
  • Relevance Feedback:  A computational model that adjusts the criteria for implicitly identifying responsive documents following feedback by a knowledgeable user as to which documents are relevant and which are not.

Kroll Ontrack (Intelligent Review Technology (IRT) | Ontrack® Inview™)

  • Active Learning: An iterative process that presents for reviewer judgment those documents that are most likely to be misclassified.  In conjunction with Support Vector Machines, it presents those documents that are closest to the current position of the separating line.  The line is moved if any of the presented documents has been misclassified.
  • Other:  Logistical Regression is well-accepted by computer science and information retrieval communities as a sound statistical modeling approach for data analysis and predictive modeling.  Logistic regression is a form of supervised learning, in that a logistic regression model is produced by “training” on a set of documents that have been manually categorized.  Once trained, the logistic regression model can be used to estimate the probability that a new document belongs to each of the possible categories. The model can use both content features such as words and phrases, and metadata features such as custodian, date, file type, and contextual information. They can be applied to data sets with millions of documents and billions of content features, and are one of the most effective approaches in a wide range of text and data mining tasks.

Liquid Litigation Management (Technology-Assisted Review) @LLMinc

  • Active Learning: An iterative process that presents for reviewer judgment those documents that are most likely to be misclassified.  In conjunction with Support Vector Machines, it presents those documents that are closest to the current position of the separating line.  The line is moved if any of the presented documents has been misclassified.
  • Latent Semantic Analysis:  A mathematical approach that seeks to summarize the meaning of words by looking at the documents that share those words.  LSA builds up a mathematical model of how words are related to documents and lets users take advantage of these computed relations to categorize documents.

Nuix (Automatic Classification) @Nuix

  • Naïve Bayesian Classifier:  A system that examines the probability that each word in a new document came from the word distribution derived from trained responsive document or from trained non-responsive documents.  The system is naïve in the sense that it assumes that all words are independent of one another.

Orange Legal Technologies (Predictive Review | OrcaTec) @OrangeLT 

  • Language Modeling:  A mathematical approach that seeks to summarize the meaning of words by looking at how they are used in the set of documents.  Language modeling in predictive coding builds a model for word occurrence in the responsive and in the non-responsive documents and classifies documents according to the model that best accounts for the words in a document being considered.

 OrcaTec (OrcaPredict) @OrcaTec

  • Language Modeling:  A mathematical approach that seeks to summarize the meaning of words by looking at how they are used in the set of documents.  Language modeling in predictive coding builds a model for word occurrence in the responsive and in the non-responsive documents and classifies documents according to the model that best accounts for the words in a document being considered.

Prolorem (Prolorem eDi)

  • Support Vector Machine:  A mathematical approach that seeks to find a line that separates responsive from non-responsive documents so that, ideally, all of the responsive documents are on one side of the line and all of the non-responsive ones are on the other side.

Recommind (Predictive Coding | Axelerate) @Recommind

  • Probabilistic Latent Semantic Analysis:  A second mathematical approach that seeks to summarize the meaning of words by looking at the documents that share those words.  PLSA builds up a mathematical model of how words are related to documents and lets users take advantage of these computed relations to categorize documents.
  • Support Vector Machine:  A mathematical approach that seeks to find a line that separates responsive from non-responsive documents so that, ideally, all of the responsive documents are on one side of the line and all of the non-responsive ones are on the other side.

Servient (Servient Predictive Review) @Servient

  • Active Learning: An iterative process that presents for reviewer judgment those documents that are most likely to be misclassified.  In conjunction with Support Vector Machines, it presents those documents that are closest to the current position of the separating line.  The line is moved if any of the presented documents has been misclassified.
  • Language Modeling:  A mathematical approach that seeks to summarize the meaning of words by looking at how they are used in the set of documents.  Language modeling in predictive coding builds a model for word occurrence in the responsive and in the non-responsive documents and classifies documents according to the model that best accounts for the words in a document being considered.
  • Latent Semantic Analysis:  A mathematical approach that seeks to summarize the meaning of words by looking at the documents that share those words.  LSA builds up a mathematical model of how words are related to documents and lets users take advantage of these computed relations to categorize documents.
  • Linguistic Analysis:  Linguists examine responsive and non-responsive documents to derive classification rules that maximize the correct classification of documents.
  • Naïve Bayesian Classifier:  A system that examines the probability that each word in a new document came from the word distribution derived from trained responsive document or from trained non-responsive documents.  The system is naïve in the sense that it assumes that all words are independent of one another.
  • Nearest Neighbor Classifier:  A classification system that categorizes documents by finding an already classified example that is very similar (near) to the document being considered. It gives the new document the same category as the most similar trained example.
  • Relevance Feedback:  A computational model that adjusts the criteria for implicitly identifying responsive documents following feedback by a knowledgeable user as to which documents are relevant and which are not.
  • Support Vector Machine:  A mathematical approach that seeks to find a line that separates responsive from non-responsive documents so that, ideally, all of the responsive documents are on one side of the line and all of the non-responsive ones are on the other side.

Symantec (Clearwell Systems) (Transparent Predictive Coding) @SYMCeDiscovery

  • Active Learning: An iterative process that presents for reviewer judgment those documents that are most likely to be misclassified.  In conjunction with Support Vector Machines, it presents those documents that are closest to the current position of the separating line.  The line is moved if any of the presented documents has been misclassified.
  • Relevance Feedback:  A computational model that adjusts the criteria for implicitly identifying responsive documents following feedback by a knowledgeable user as to which documents are relevant and which are not.
  • Support Vector Machine:  A mathematical approach that seeks to find a line that separates responsive from non-responsive documents so that, ideally, all of the responsive documents are on one side of the line and all of the non-responsive ones are on the other side.

TCDI (Suggestive Coding | Content Analyst)

  • Latent Semantic Analysis:  A mathematical approach that seeks to summarize the meaning of words by looking at the documents that share those words.  LSA builds up a mathematical model of how words are related to documents and lets users take advantage of these computed relations to categorize documents.

UBIC (CJK TAR)

  • Active Learning: An iterative process that presents for reviewer judgment those documents that are most likely to be misclassified.  In conjunction with Support Vector Machines, it presents those documents that are closest to the current position of the separating line.  The line is moved if any of the presented documents has been misclassified.
  • Language Modeling:  A mathematical approach that seeks to summarize the meaning of words by looking at how they are used in the set of documents.  Language modeling in predictive coding builds a model for word occurrence in the responsive and in the non-responsive documents and classifies documents according to the model that best accounts for the words in a document being considered.
  • Latent Semantic Analysis:  A mathematical approach that seeks to summarize the meaning of words by looking at the documents that share those words.  LSA builds up a mathematical model of how words are related to documents and lets users take advantage of these computed relations to categorize documents.
  • Nearest Neighbor Classifier:  A classification system that categorizes documents by finding an already classified example that is very similar (near) to the document being considered. It gives the new document the same category as the most similar trained example.
  • Probabilistic Latent Semantic Analysis:  A second mathematical approach that seeks to summarize the meaning of words by looking at the documents that share those words.  PLSA builds up a mathematical model of how words are related to documents and lets users take advantage of these computed relations to categorize documents.
  • Relevance Feedback:  A computational model that adjusts the criteria for implicitly identifying responsive documents following feedback by a knowledgeable user as to which documents are relevant and which are not.
  • Support Vector Machine:  A mathematical approach that seeks to find a line that separates responsive from non-responsive documents so that, ideally, all of the responsive documents are on one side of the line and all of the non-responsive ones are on the other side.

Valora Technologies (Valora Auto Review Services) @ValoraTech

  • Other:  Probabilistic Hierarchical Context-Free Grammars approach to machine learning.

Xerox Litigation Services (CategoriX) @Xerox_XLS

  • Active Learning: An iterative process that presents for reviewer judgment those documents that are most likely to be misclassified.  In conjunction with Support Vector Machines, it presents those documents that are closest to the current position of the separating line.  The line is moved if any of the presented documents has been misclassified.
  • Language Modeling:  A mathematical approach that seeks to summarize the meaning of words by looking at how they are used in the set of documents.  Language modeling in predictive coding builds a model for word occurrence in the responsive and in the non-responsive documents and classifies documents according to the model that best accounts for the words in a document being considered.
  • Linguistic Analysis:  Linguists examine responsive and non-responsive documents to derive classification rules that maximize the correct classification of documents.
  • Probabilistic Latent Semantic Analysis:  A second mathematical approach that seeks to summarize the meaning of words by looking at the documents that share those words.  PLSA builds up a mathematical model of how words are related to documents and lets users take advantage of these computed relations to categorize documents.
  • Relevance Feedback:  A computational model that adjusts the criteria for implicitly identifying responsive documents following feedback by a knowledgeable user as to which documents are relevant and which are not.
  • Support Vector Machine:  A mathematical approach that seeks to find a line that separates responsive from non-responsive documents so that, ideally, all of the responsive documents are on one side of the line and all of the non-responsive ones are on the other side.

Current Responses (By Answer)

Active Learning

Active Learning: An iterative process that presents for reviewer judgment those documents that are most likely to be misclassified.  In conjunction with Support Vector Machines, it presents those documents that are closest to the current position of the separating line.  The line is moved if any of the presented documents has been misclassified.

  • Altep
  • BIA
  • Content Analyst
  • D4
  • Daegis
  • Driven
  • Kroll Ontrack
  • Liquid Litigation Management (LLM)
  • Servient
  • Symantec/Clearwell
  • UBIC
  • Xerox Litigation Services

Language Modeling

Language Modeling:  A mathematical approach that seeks to summarize the meaning of words by looking at how they are used in the set of documents.  Language modeling in predictive coding builds a model for word occurrence in the responsive and in the non-responsive documents and classifies documents according to the model that best accounts for the words in a document being considered.

  • BIA
  • Orange Legel Technologies
  • OrcaTec
  • Servient
  • UBIC
  • Xerox Litigation Services

Latent Semantic Analysis

Latent Semantic Analysis:  A mathematical approach that seeks to summarize the meaning of words by looking at the documents that share those words.  LSA builds up a mathematical model of how words are related to documents and lets users take advantage of these computed relations to categorize documents.

  • Altep
  • BIA
  • Content Analyst
  • Driven
  • kCura
  • Liquid Litigation Management (LLM)
  • Servient
  • TCDI
  • UBIC

Linguistic Analysis

Linguistic Analysis:  Linguists examine responsive and non-responsive documents to derive classification rules that maximize the correct classification of documents.

  • BIA
  • Servient
  • Xerox Litigation Services

Naive Bayesian Classifier

Naïve Bayesian Classifier:  A system that examines the probability that each word in a new document came from the word distribution derived from trained responsive document or from trained non-responsive documents.  The system is naïve in the sense that it assumes that all words are independent of one another.

  • BIA
  • Nuix
  • Servient

Nearest Neighbor Classifier

Nearest Neighbor Classifier:  A classification system that categorizes documents by finding an already classified example that is very similar (near) to the document being considered. It gives the new document the same category as the most similar trained example.

  • @Legal
  • BIA
  • Catalyst Repository Systems
  • Driven
  • Huron Legal
  • kCura
  • Servient
  • UBIC

Probabilistic Latent Semantic Analysis

Probabilistic Latent Semantic Analysis:  A second mathematical approach that seeks to summarize the meaning of words by looking at the documents that share those words.  PLSA builds up a mathematical model of how words are related to documents and lets users take advantage of these computed relations to categorize documents.

  • BIA
  • Daegis
  • Recommind
  • UBIC
  • Xerox Litigation Services

Relevance Feedback

Relevance Feedback:  A computational model that adjusts the criteria for implicitly identifying responsive documents following feedback by a knowledgeable user as to which documents are relevant and which are not.

  • BIA
  • Driven
  • kCura
  • Servient
  • Symantec/Clearwell
  • UBIC
  • Xerox Litigation Services

Support Vector Machine

Support Vector Machine:  A mathematical approach that seeks to find a line that separates responsive from non-responsive documents so that, ideally, all of the responsive documents are on one side of the line and all of the non-responsive ones are on the other side.

  • @Legal
  • BIA
  • D4
  • Prolorem
  • Recommind
  • Servient
  • Symantec/Clearwell
  • UBIC
  • Xerox Litigation Services

Other: Logistical Regression

  • Kroll Ontrack

Other: Probabilistic Hierarchical Context-Free Grammars

  • Valora Technologies

End of Survey Results

PredictiveCoding-Words

 

 

Have a Request?

If you have information or offering requests that you would like to ask us about, please let us know, and we will make our response to you a priority.

ComplexDiscovery OÜ is a highly recognized digital publication focused on providing detailed insights into the fields of cybersecurity, information governance, and eDiscovery. Based in Estonia, a hub for digital innovation, ComplexDiscovery OÜ upholds rigorous standards in journalistic integrity, delivering nuanced analyses of global trends, technology advancements, and the eDiscovery sector. The publication expertly connects intricate legal technology issues with the broader narrative of international business and current events, offering its readership invaluable insights for informed decision-making.

For the latest in law, technology, and business, visit ComplexDiscovery.com.

 

Generative Artificial Intelligence and Large Language Model Use

ComplexDiscovery OÜ recognizes the value of GAI and LLM tools in streamlining content creation processes and enhancing the overall quality of its research, writing, and editing efforts. To this end, ComplexDiscovery OÜ regularly employs GAI tools, including ChatGPT, Claude, DALL-E2, Grammarly, Midjourney, and Perplexity, to assist, augment, and accelerate the development and publication of both new and revised content in posts and pages published (initiated in late 2022).

ComplexDiscovery also provides a ChatGPT-powered AI article assistant for its users. This feature leverages LLM capabilities to generate relevant and valuable insights related to specific page and post content published on ComplexDiscovery.com. By offering this AI-driven service, ComplexDiscovery OÜ aims to create a more interactive and engaging experience for its users, while highlighting the importance of responsible and ethical use of GAI and LLM technologies.