Thu. Apr 18th, 2024
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CONTENT released online between 1 April 2010 and 24 August 2018 or content that has been selectively archived and is no longer active.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.
 

120 Seconds of Predictive Coding – Survey Results

Provided below for your consideration and use are the in-progress results of the Predictive Coding and Providers: A 120-Second Survey launched by ComplexDiscovery on 2/10/13.  The goal of the survey is to provide a quick, non-comprehensive overview of the use of the technology-assisted review feature of predictive coding among leading eDiscovery providers as represented by those providers. The areas covered in the short survey include:

  • Technology Development (Developed Internally, Licensed Externally or Hybrid Development)
  • Technology Partners (Content Analyst, Equivio, OrcaTec, Recommind or Other)
  • Offering Integration (Architectural Integration, Process Integration or Other)
  • Machine Learning Approach (Supervised Learning, Active Learning or Other)
  • Sampling Approach (Random, Judgmental or Other)

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.

Updated 7/23/2013

Current Responders

  • @Legal
  • AccessData
  • AlphaLit
  • Altep
  • BIA
  • Catalyst Repository Systems
  • Content Analyst
  • D4
  • Daegis
  • Deloitte
  • Driven
  • DTI
  • Equivio
  • Exterro
  • Hudson Legal
  • Huron Legal
  • kCura
  • Kroll Ontrack
  • NightOwl Discovery
  • Nuix
  • Orange Legal Technologies
  • OrcaTec
  • Prolorem
  • Rational Retention
  • Recommind
  • RenewData
  • Servient
  • Symantec/Clearwell
  • TCDI
  • UBIC
  • UHY Advisors
  • Valora Technologies
  • Xerox Litigation Services
  • ZyLAB

Current Responses (By Provider)

@Legal (CasePoint TAR) @AtLegal

  • Developed Internally: Proprietary development of predictive coding technology.
  • Architecturally Integrated: Predictive coding technology is integrated into the software architecture (application integration) of core eDiscovery platform.
  • Supervised Learning: Human chooses a set of documents (training set) and feeds the documents into the system. The system learns the difference between responsive and non-responsive documents and classifies remaining documents accordingly.
  • Random Sampling: A statistical sampling approach that gives each document an equal chance of being chosen for inclusion within a sample.
  • Judgmental Sampling: A sampling approach that draws in part from subjective factors when determining inclusion within a sample.

AccessData (Summation – Predictive Coding Feature) @AccessData Group 

  • Developed Internally: Proprietary development of predictive coding technology.
  • Architecturally Integrated: Predictive coding technology is integrated into the software architecture (application integration) of core eDiscovery platform.
  • Supervised Learning: Human chooses a set of documents (training set) and feeds the documents into the system. The system learns the difference between responsive and non-responsive documents and classifies remaining documents accordingly.
  • Judgmental Sampling: A sampling approach that draws in part from subjective factors when determining inclusion within a sample.

AlphaLit (E-Predict | Backstop – Content Analyst)

  • Hybrid Development: Combination of proprietary and licensed predictive coding technology.
  • Technology Partners:  Backstop, Content Analyst
  • Architecturally Integrated: Predictive coding technology is integrated into the software architecture (application integration) of core eDiscovery platform.
  • Supervised Learning: Human chooses a set of documents (training set) and feeds the documents into the system. The system learns the difference between responsive and non-responsive documents and classifies remaining documents accordingly.
  • Random Sampling: A statistical sampling approach that gives each document an equal chance of being chosen for inclusion within a sample.

Altep (Tag | Content Analyst) @Altep_Inc

  • Developed Internally: Proprietary development of predictive coding technology.
  • Technology Partners:  Content Analyst
  • Architecturally Integrated: Predictive coding technology is integrated into the software architecture (application integration) of core eDiscovery platform. (Available as a standalone application and integrated into the Inspicio offering.)
  • Supervised Learning: Human chooses a set of documents (training set) and feeds the documents into the system. The system learns the difference between responsive and non-responsive documents and classifies remaining documents accordingly.
  • Active Learning: System chooses a set of documents and feeds the documents to humans. Humans make a decision about the documents and then the system applies the learning provided by the humans against the rest of the documents in the collection.
  • Random Sampling: A statistical sampling approach that gives each document an equal chance of being chosen for inclusion within a sample.

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

  • Developed Internally: Proprietary development of predictive coding technology.
  • Architecturally Integrated: Predictive coding technology is integrated into the software architecture (application integration) of core eDiscovery platform.
  • Process Integrated: Predictive coding technology is available as an eDiscovery offering, but not integrated into the software architecture of core eDiscovery platform (process integration).
  • Supervised Learning: Human chooses a set of documents (training set) and feeds the documents into the system. The system learns the difference between responsive and non-responsive documents and classifies remaining documents accordingly.
  • Active Learning: System chooses a set of documents and feeds the documents to humans. Humans make a decision about the documents and then the system applies the learning provided by the humans against the rest of the documents in the collection.
  • Random Sampling: A statistical sampling approach that gives each document an equal chance of being chosen for inclusion within a sample.
  • Judgmental Sampling: A sampling approach that draws in part from subjective factors when determining inclusion within a sample.

Catalyst Repository Systems (Insight Predict) @CatalystSecure

  • Developed Internally: Proprietary development of predictive coding technology.
  • Architecturally Integrated: Predictive coding technology is integrated into the software architecture (application integration) of core eDiscovery platform.
  • Globally Adaptive K-Nearest Neighbor machine learning approach.
  • Random Sampling: A statistical sampling approach that gives each document an equal chance of being chosen for inclusion within a sample.
  • Judgmental Sampling: A sampling approach that draws in part from subjective factors when determining inclusion within a sample.

Content Analyst (Conceptual Categorization) @Content_Analyst

  • Developed Internally: Proprietary development of predictive coding technology. (Content Analyst provides analytics technology, not end user solutions).
  • Architecturally Integrated: Predictive coding technology is integrated into the software architecture (application integration) of core eDiscovery platform.
  • Supervised Learning: Human chooses a set of documents (training set) and feeds the documents into the system. The system learns the difference between responsive and non-responsive documents and classifies remaining documents accordingly (based on licensee approach).
  • Active Learning: System chooses a set of documents and feeds the documents to humans. Humans make a decision about the documents and then the system applies the learning provided by the humans against the rest of the documents in the collection (based on licensee approach).
  • Random Sampling: A statistical sampling approach that gives each document an equal chance of being chosen for inclusion within a sample (based on licensee approach).
  • Judgmental Sampling: A sampling approach that draws in part from subjective factors when determining inclusion within a sample (based on licensee approach).

D4 Discovery (Equivio Relevance – Relativity Assisted Review) @D4Discovery

  • Licensed Externally: Predictive coding technology completely licensed from software developer.
  • Technology Partners:  Equivio, Content Analyst
  • Architecturally Integrated: Predictive coding technology is integrated into the software architecture (application integration) of core eDiscovery platform.
  • Active Learning: System chooses a set of documents and feeds the documents to humans. Humans make a decision about the documents and then the system applies the learning provided by the humans against the rest of the documents in the collection.
  • Random Sampling: A statistical sampling approach that gives each document an equal chance of being chosen for inclusion within a sample.
  • Judgmental Sampling: A sampling approach that draws in part from subjective factors when determining inclusion within a sample.

Daegis (Acumen) @Daegis

  • Developed Internally: Proprietary development of predictive coding technology.
  • Architecturally Integrated: Predictive coding technology is integrated into the software architecture (application integration) of core eDiscovery platform.
  • Active Learning: System chooses a set of documents and feeds the documents to humans. Humans make a decision about the documents and then the system applies the learning provided by the humans against the rest of the documents in the collection.
  • Random Sampling: A statistical sampling approach that gives each document an equal chance of being chosen for inclusion within a sample.

Deloitte (Dynamic Review) @DeloitteFinSvcs

  • Developed Internally: Proprietary development of predictive coding technology.
  • Process Integrated: Predictive coding technology is available as an eDiscovery offering, but not integrated into the software architecture of core eDiscovery platform (process integration).
  • Supervised Learning: Human chooses a set of documents (training set) and feeds the documents into the system. The system learns the difference between responsive and non-responsive documents and classifies remaining documents accordingly.
  • Random Sampling: A statistical sampling approach that gives each document an equal chance of being chosen for inclusion within a sample.
  • Judgmental Sampling: A sampling approach that draws in part from subjective factors when determining inclusion within a sample.

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

  • Developed Internally: Proprietary development of predictive coding technology.
  • Technology Partners:  Content Analyst
  • Architecturally Integrated: Predictive coding technology is integrated into the software architecture (application integration) of core eDiscovery platform.
  • Supervised Learning: Human chooses a set of documents (training set) and feeds the documents into the system. The system learns the difference between responsive and non-responsive documents and classifies remaining documents accordingly.
  • Random Sampling: A statistical sampling approach that gives each document an equal chance of being chosen for inclusion within a sample.

DTI (Technology-Assisted Review | Equivio)

  • Licensed Externally: Predictive coding technology completely licensed from software developer.
  • Technology Partner:  Equivio
  • Process Integrated: Predictive coding technology is available as an eDiscovery offering, but not integrated into the software architecture of core eDiscovery platform (process integration).
  • Active Learning: System chooses a set of documents and feeds the documents to humans. Humans make a decision about the documents and then the system applies the learning provided by the humans against the rest of the documents in the collection.
  • Random Sampling: A statistical sampling approach that gives each document an equal chance of being chosen for inclusion within a sample.

Equivio (Relevance) @Equivio

  • Developed Internally: Proprietary development of predictive coding technology.
  • Architecturally Integrated: Predictive coding technology is integrated into the software architecture (application integration) of core eDiscovery platform.
  • Active Learning: System chooses a set of documents and feeds the documents to humans. Humans make a decision about the documents and then the system applies the learning provided by the humans against the rest of the documents in the collection.
  • Random Sampling: A statistical sampling approach that gives each document an equal chance of being chosen for inclusion within a sample.

Exterro (Fusion Predictive Intelligence™) @Exterro

  • Developed Internally: Proprietary development of predictive coding technology.
  • Architecturally Integrated: Predictive coding technology is integrated into the software architecture (application integration) of core eDiscovery platform.
  • Supervised Learning: Human chooses a set of documents (training set) and feeds the documents into the system. The system learns the difference between responsive and non-responsive documents and classifies remaining documents accordingly.
  • Active Learning: System chooses a set of documents and feeds the documents to humans. Humans make a decision about the documents and then the system applies the learning provided by the humans against the rest of the documents in the collection.
  • Random Sampling: A statistical sampling approach that gives each document an equal chance of being chosen for inclusion within a sample.
  • Judgmental Sampling: A sampling approach that draws in part from subjective factors when determining inclusion within a sample.

Hudson Legal (Predictive Coding | Recommind – Relativity – Kroll Ontrack) @HudsonLegal

  • Licensed Externally: Predictive coding technology completely licensed from software developer.
  • Technology Partner:  Recommind (Offer Relativity and Kroll Ontrack capabilities also.)
  • Process Integrated: Predictive coding technology is available as an eDiscovery offering, but not integrated into the software architecture of core eDiscovery platform (process integration).
  • Active Learning: System chooses a set of documents and feeds the documents to humans. Humans make a decision about the documents and then the system applies the learning provided by the humans against the rest of the documents in the collection.
  • Random Sampling: A sampling approach that gives each document an equal chance of being chosen for inclusion within a sample.

Huron Legal (Integrated Analytics | PureDiscovery) @HuronLegal

  • Licensed Externally: Predictive coding technology completely licensed from software developer.
  • Technology Partner:  PureDiscovery
  • Process Integrated: Predictive coding technology is available as an eDiscovery offering, but not integrated into the software architecture of core eDiscovery platform (process integration).
  • Supervised Learning: Human chooses a set of documents (training set) and feeds the documents into the system. The system learns the difference between responsive and non-responsive documents and classifies remaining documents accordingly.
  • Random Sampling: A statistical sampling approach that gives each document an equal chance of being chosen for inclusion within a sample.
  • Judgmental Sampling: A sampling approach that draws in part from subjective factors when determining inclusion within a sample.

kCura (Relativity Assisted Review | Content Analyst) @kCura

  • Hybrid Development: Combination of proprietary and licensed predictive coding technology.
  • Technology Partner:  Content Analyst
  • Architecturally Integrated: Predictive coding technology is integrated into the software architecture (application integration) of core eDiscovery platform.
  • Supervised Learning: Human chooses a set of documents (training set) and feeds the documents into the system. The system learns the difference between responsive and non-responsive documents and classifies remaining documents accordingly.
  • Active Learning: System chooses a set of documents and feeds the documents to humans. Humans make a decision about the documents and then the system applies the learning provided by the humans against the rest of the documents in the collection.
  • Random Sampling: A statistical sampling approach that gives each document an equal chance of being chosen for inclusion within a sample.
  • Judgmental Sampling: A sampling approach that draws in part from subjective factors when determining inclusion within a sample.

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

  • Developed Internally: Proprietary development of predictive coding technology.
  • Architecturally Integrated: Predictive coding technology is integrated into the software architecture (application integration) of core eDiscovery platform.
  • Supervised Learning: Human chooses a set of documents (training set) and feeds the documents into the system. The system learns the difference between responsive and non-responsive documents and classifies remaining documents accordingly.
  • Active Learning: System chooses a set of documents and feeds the documents to humans. Humans make a decision about the documents and then the system applies the learning provided by the humans against the rest of the documents in the collection.
  • Random Sampling: A statistical sampling approach that gives each document an equal chance of being chosen for inclusion within a sample.
  • Judgmental Sampling: A sampling approach that draws in part from subjective factors when determining inclusion within a sample.

NightOwl Discovery (Predictive Coding | Equivio – Relativity) @NightOwlDMS 

  • Licensed Externally: Predictive coding technology completely licensed from software developer.
  • Technology Partners: Equivio, Relativity
  • Architecturally Integrated: Predictive coding technology is integrated into the software architecture (application integration) of core eDiscovery platform.
  • Supervised Learning: Human chooses a set of documents (training set) and feeds the documents into the system. The system learns the difference between responsive and non-responsive documents and classifies remaining documents accordingly.
  • Active Learning: System chooses a set of documents and feeds the documents to humans. Humans make a decision about the documents and then the system applies the learning provided by the humans against the rest of the documents in the collection.
  • Random Sampling: A statistical sampling approach that gives each document an equal chance of being chosen for inclusion within a sample.
  • Judgmental Sampling: A sampling approach that draws in part from subjective factors when determining inclusion within a sample.

Nuix (Automatic Classification) @Nuix

  • Developed Internally: Proprietary development of predictive coding technology.
  • Architecturally Integrated: Predictive coding technology is integrated into the software architecture (application integration) of core eDiscovery platform.
  • Supervised Learning: Human chooses a set of documents (training set) and feeds the documents into the system. The system learns the difference between responsive and non-responsive documents and classifies remaining documents accordingly.
  • Judgmental Sampling: A sampling approach that draws in part from subjective factors when determining inclusion within a sample.

Orange Legal Technologies (Predictive Review | OrcaTec) @OrangeLT

  • Hybrid Development: Combination of proprietary and licensed predictive coding technology.
  • Technology Partner:  OrcaTec
  • Architecturally Integrated: Predictive coding technology is integrated into the software architecture (application integration) of core eDiscovery platform.
  • Active Learning: System chooses a set of documents and feeds the documents to humans. Humans make a decision about the documents and then the system applies the learning provided by the humans against the rest of the documents in the collection.
  • Random Sampling: A statistical sampling approach that gives each document an equal chance of being chosen for inclusion within a sample.

 OrcaTec (OrcaPredict) @OrcaTec

  • Developed Internally: Proprietary development of predictive coding technology.
  • Architecturally Integrated: Predictive coding technology is integrated into the software architecture (application integration) of core eDiscovery platform.
  • Active Learning: System chooses a set of documents and feeds the documents to humans. Humans make a decision about the documents and then the system applies the learning provided by the humans against the rest of the documents in the collection.
  • Random Sampling: A statistical sampling approach that gives each document an equal chance of being chosen for inclusion within a sample.

Prolorem (Prolorem eDi)

  • Hybrid Development: Combination of proprietary and licensed predictive coding technology.
  • Technology Partners:  Open Source Licensed APIs and Tools
  • Architecturally Integrated: Predictive coding technology is integrated into the software architecture (application integration) of core eDiscovery platform.
  • Supervised Learning: Human chooses a set of documents (training set) and feeds the documents into the system. The system learns the difference between responsive and non-responsive documents and classifies remaining documents accordingly.
  • Random Sampling: A statistical sampling approach that gives each document an equal chance of being chosen for inclusion within a sample.

Rational Retention (Rational Intelligence)

  • Developed Internally: Proprietary development of predictive coding technology.
  • Process Integrated: Predictive coding technology is available as an eDiscovery offering, but not integrated into the software architecture of core eDiscovery platform (process integration).
  • Supervised Learning: Human chooses a set of documents (training set) and feeds the documents into the system. The system learns the difference between responsive and non-responsive documents and classifies remaining documents accordingly.
  • Random Sampling: A statistical sampling approach that gives each document an equal chance of being chosen for inclusion within a sample.
  • Judgmental Sampling: A sampling approach that draws in part from subjective factors when determining inclusion within a sample.

Recommind (Predictive Coding | Axelerate) @Recommind

  • Developed Internally: Proprietary development of predictive coding technology.
  • Architecturally Integrated: Predictive coding technology is integrated into the software architecture (application integration) of core eDiscovery platform.
  • Supervised Learning: Human chooses a set of documents (training set) and feeds the documents into the system. The system learns the difference between responsive and non-responsive documents and classifies remaining documents accordingly.
  • Random Sampling: A statistical sampling approach that gives each document an equal chance of being chosen for inclusion within a sample.

RenewData (Computer-Assisted Coding | Equivio – Content Analyst) @RenewData

  • Licensed Externally: Predictive coding technology completely licensed from software developer.
  • Technology Partners:  Equivio, Content Analyst
  • Process Integrated: Predictive coding technology is available as an eDiscovery offering, but not integrated into the software architecture of core eDiscovery platform (process integration).
  • Supervised Learning: Human chooses a set of documents (training set) and feeds the documents into the system. The system learns the difference between responsive and non-responsive documents and classifies remaining documents accordingly.
  • Random Sampling: A statistical sampling approach that gives each document an equal chance of being chosen for inclusion within a sample.

Servient (Servient Predictive Review) @Servient

  • Developed Internally: Proprietary development of predictive coding technology.
  • Architecturally Integrated: Predictive coding technology is integrated into the software architecture (application integration) of core eDiscovery platform.
  • Supervised Learning: Human chooses a set of documents (training set) and feeds the documents into the system. The system learns the difference between responsive and non-responsive documents and classifies remaining documents accordingly.
  • Active Learning: System chooses a set of documents and feeds the documents to humans. Humans make a decision about the documents and then the system applies the learning provided by the humans against the rest of the documents in the collection.
  • Random Sampling: A statistical sampling approach that gives each document an equal chance of being chosen for inclusion within a sample.
  • Judgmental Sampling: A sampling approach that draws in part from subjective factors when determining inclusion within a sample.

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

  • Developed Internally: Proprietary development of predictive coding technology.
  • Architecturally Integrated: Predictive coding technology is integrated into the software architecture (application integration) of core eDiscovery platform.
  • Supervised Learning: Human chooses a set of documents (training set) and feeds the documents into the system. The system learns the difference between responsive and non-responsive documents and classifies remaining documents accordingly.
  • Active Learning: System chooses a set of documents and feeds the documents to humans. Humans make a decision about the documents and then the system applies the learning provided by the humans against the rest of the documents in the collection.
  • Random Sampling: A statistical sampling approach that gives each document an equal chance of being chosen for inclusion within a sample.
  • Judgmental Sampling: A sampling approach that draws in part from subjective factors when determining inclusion within a sample.

TCDI (Suggestive Coding | Content Analyst)

  • Hybrid Development: Combination of proprietary and licensed predictive coding technology.
  • Technology Partner:  Content Analyst
  • Architecturally Integrated: Predictive coding technology is integrated into the software architecture (application integration) of core eDiscovery platform.
  • Supervised Learning: Human chooses a set of documents (training set) and feeds the documents into the system. The system learns the difference between responsive and non-responsive documents and classifies remaining documents accordingly.
  • Active Learning: System chooses a set of documents and feeds the documents to humans. Humans make a decision about the documents and then the system applies the learning provided by the humans against the rest of the documents in the collection.
  • Random Sampling: A statistical sampling approach that gives each document an equal chance of being chosen for inclusion within a sample.
  • Judgmental Sampling: A sampling approach that draws in part from subjective factors when determining inclusion within a sample.

UBIC (CJK TAR)

  • Developed Internally: Proprietary development of predictive coding technology.
  • Architecturally Integrated: Predictive coding technology is integrated into the software architecture (application integration) of core eDiscovery platform.
  • Supervised Learning: Human chooses a set of documents (training set) and feeds the documents into the system. The system learns the difference between responsive and non-responsive documents and classifies remaining documents accordingly.
  • Active Learning: System chooses a set of documents and feeds the documents to humans. Humans make a decision about the documents and then the system applies the learning provided by the humans against the rest of the documents in the collection.
  • Random Sampling: A statistical sampling approach that gives each document an equal chance of being chosen for inclusion within a sample.
  • Judgmental Sampling: A sampling approach that draws in part from subjective factors when determining inclusion within a sample.

UHY Advisors (Assisted Review | Relativity)

  • Licensed Externally: Predictive coding technology completely licensed from software developer.
  • Technology Partners: Relativity
  • Architecturally Integrated: Predictive coding technology is integrated into the software architecture (application integration) of core eDiscovery platform.
  • Supervised Learning: Human chooses a set of documents (training set) and feeds the documents into the system. The system learns the difference between responsive and non-responsive documents and classifies remaining documents accordingly.
  • Active Learning: System chooses a set of documents and feeds the documents to humans. Humans make a decision about the documents and then the system applies the learning provided by the humans against the rest of the documents in the collection.
  • Random Sampling: A statistical sampling approach that gives each document an equal chance of being chosen for inclusion within a sample.
  • Judgmental Sampling: A sampling approach that draws in part from subjective factors when determining inclusion within a sample.

Valora Technologies (Valora Auto Review Services) @ValoraTech

  • Developed Internally: Proprietary development of predictive coding technology.
  • Architecturally Integrated: Predictive coding technology is integrated into the software architecture (application integration) of core eDiscovery platform.
  • Probabilistic Hierarchical Context-Free Grammars approach to machine learning.
  • Stratified Sampling: A statistical sampling approach in which populations are stratified by attributes (which can be automatically obtained or obtained from human input), then selected for sampling so that the sample strata match the population strata.

Xerox Litigation Services (CategoriX) @Xerox_XLS

  • Developed Internally: Proprietary development of predictive coding technology.
  • Architecturally Integrated: Predictive coding technology is integrated into the software architecture (application integration) of core eDiscovery platform.
  • Supervised Learning: Human chooses a set of documents (training set) and feeds the documents into the system. The system learns the difference between responsive and non-responsive documents and classifies remaining documents accordingly.
  • Random Sampling: A statistical sampling approach that gives each document an equal chance of being chosen for inclusion within a sample.
  • Judgmental Sampling: A sampling approach that draws in part from subjective factors when determining inclusion within a sample.

Xerox Litigation Services – Lateral Data (View Point Assisted Review) @Xerox_XLS

  • Developed Internally: Proprietary development of predictive coding technology.
  • Architecturally Integrated: Predictive coding technology is integrated into the software architecture (application integration) of core eDiscovery platform.
  • Active Learning: System chooses a set of documents and feeds the documents to humans. Humans make a decision about the documents and then the system applies the learning provided by the humans against the rest of the documents in the collection.
  • Random Sampling: A statistical sampling approach that gives each document an equal chance of being chosen for inclusion within a sample.
  • Judgmental Sampling: A sampling approach that draws in part from subjective factors when determining inclusion within a sample.

ZyLAB (ZyLAB Technology-Assisted Review) @ZyLAB

  • Developed Internally: Proprietary development of predictive coding technology.
  • Architecturally Integrated: Predictive coding technology is integrated into the software architecture (application integration) of core eDiscovery platform.
  • Supervised Learning: Human chooses a set of documents (training set) and feeds the documents into the system. The system learns the difference between responsive and non-responsive documents and classifies remaining documents accordingly.
  • Random Sampling: A statistical sampling approach that gives each document an equal chance of being chosen for inclusion within a sample.

Current Responses (By Answer)

Technology Development

Developed Internally: Proprietary development of predictive coding technology.

  • @Legal
  • AccessData
  • Altep
  • BIA
  • Catalyst Repository Systems
  • Content Analyst (Content Analyst provides analytics technology, not end user solutions).
  • Daegis
  • Deloitte
  • Driven
  • Equivio
  • Exterro
  • Nuix
  • OrcaTec
  • Kroll Ontrack
  • Rational Retention
  • Recommind
  • Servient
  • Symantec/Clearwell
  • UBIC
  • Valora Technologies
  • Xerox Litigation Services (Viewpoint Assisted Review and CategoriX)
  • ZyLAB

Licensed Externally: Predictive coding technology completely licensed from software developer.

  • D4 (Equivio, Content Analyst)
  • DTI (Equivio)
  • Hudson Legal
  • Huron Legal (PureDiscovery)
  • NightOwl Discovery
  • RenewData (Equivio, Content Analyst)
  • UHY Advisors

Hybrid Development: Combination of proprietary and licensed predictive coding technology.

  • AlphaLit (Backstop, Content Analyst)
  • kCura (Content Analyst)
  • Orange Legal Technologies (OrcaTec)
  • Prolorem (Open Source Licensed APIs and Tools)
  • TCDI (Content Analyst)

Offering Integration

Architecturally Integrated: Predictive coding technology is integrated into the software architecture (application integration) of core eDiscovery platform.

  • @Legal
  • AccessData
  • AlphaLit
  • Altep (Available as a standalone offering or as part of the Inspicio offering.)
  • Catalyst Repository Systems
  • Content Analyst (Content Analyst provides analytics technology, not end user solutions.)
  • D4
  • Daegis
  • Driven
  • Equivio
  • Exterro
  • kCura
  • Kroll Ontrack
  • NightOwl Discovery
  • Nuix
  • OrcaTec
  • Prolorem
  • Recommind
  • Servient
  • Symantec/Clearwell
  • TCDI
  • UBIC
  • UHY Advisors
  • Valora Technologies
  • Xerox Litigation Services (Viewpoint Assisted Review and CategoriX)
  • ZyLAB

Process Integrated: Predictive coding technology is available as an eDiscovery offering, but not integrated into the software architecture of core eDiscovery platform (process integration).

  • BIA
  • DTI
  • Deloitte
  • Hudson Legal
  • Huron Legal
  • Orange Legal Technologies
  • Rational Retention
  • RenewData

Machine Learning Approach

Supervised Learning: Human chooses a set of documents (training set) and feeds the documents into the system. The system learns the difference between responsive and non-responsive documents and classifies remaining documents accordingly.

  • @Legal
  • AccessData
  • AlphaLit
  • Altep
  • BIA
  • Content Analyst (Based on licensee machine learning approach as Content Analyst provides analytics technology, not end user solutions).
  • Deloitte
  • Driven
  • Exterro
  • Huron Legal
  • kCura
  • Kroll Ontrack
  • NightOwl Discovery
  • Nuix
  • Orange Legal Technologies
  • OrcaTec
  • Prolorem
  • Rational Retention
  • Recommind
  • RenewData
  • Servient
  • Symantec/Clearwell
  • TCDI
  • UBIC
  • UHY Advisors
  • Valora Technologies
  • Xerox Litigation Services (CategoriX)
  • ZyLAB

Active Learning: System chooses a set of documents and feeds the documents to humans. Humans make a decision about the documents and then the system applies the learning provided by the humans against the rest of the documents in the collection.

  • Altep
  • BIA
  • Content Analyst (Based on licensee machine learning approach as Content Analyst provides analytics technology, not end user solutions).
  • Exterro
  • D4
  • Daegis
  • DTI
  • Equivio
  • Exterro
  • Hudson Legal
  • kCura
  • Kroll Ontrack
  • NightOwl Discovery
  • Orange Legal Technologies
  • OrcaTec
  • Servient
  • Symantec/Clearwell
  • TCDI
  • UBIC
  • UHY Advisors
  • Xerox Litigation Services (Viewpoint Assisted Review)

Other Machine Learning Approaches:

  • Catalyst Repository Systems:  Globally Adaptive K-Nearest Neighbor machine learning approach.
  • Valora Technologies: Probabilistic Hierarchical Context-Free Grammars approach to machine learning.

Sampling Approach

Random Sampling: A statistical sampling approach that gives each document an equal chance of being chosen for inclusion within a sample.

  • @Legal
  • AlphaLit
  • Altep
  • BIA
  • Catalyst Repository Systems
  • Content Analyst (Based on licensee sampling approach as Content Analyst provides analytics technology, not end user solutions).
  • Exterro
  • D4
  • Daegis
  • Deloitte
  • Driven
  • DTI
  • Equivio
  • Exterro
  • Hudson Legal
  • Huron Legal
  • kCura
  • Kroll Ontrack
  • NightOwl Discovery
  • Orange Legal Technologies
  • OrcaTec
  • Prolorem
  • Rational Retention (Preferred Method)
  • Recommind
  • RenewData
  • Servient
  • Symantec/Clearwell
  • TCDI
  • UBIC
  • UHY Advisors
  • Xerox Litigation Services (Viewpoint Assisted Review and CategoriX)
  • ZyLAB

Judgmental Sampling: A sampling approach that draws in part from subjective factors when determining inclusion within a sample.

  • @Legal
  • AccessData
  • BIA
  • Catalyst Repository Systems
  • Content Analyst (Based on licensee machine sampling approach as Content Analyst provides analytics technology, not end user solutions).
  • Exterro
  • D4
  • Deloitte
  • Exterro
  • Huron Legal
  • kCura
  • Kroll Ontrack
  • NightOwl Discovery
  • Nuix
  • Rational Retention
  • Servient
  • Symantec/Clearwell
  • TCDI
  • UBIC
  • UHY Advisors
  • Xerox Litigation Services (Viewpoint Assisted Review and CategoriX)

Other Sampling Approach

  • Valora Technologies: Stratified Sampling: A statistical sampling approach in which populations are stratified by attributes (which can be automatically obtained or obtained from human input), then selected for sampling so that the sample strata match the population strata.

End of Survey Results

Updated to remove “Statistical” from Sampling Approach “header” and from Judgmental Sampling definition.

MountainsofData

 

 

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, Midjourney, and DALL-E, 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.