Skip to content

Corporate Crime Knowledge Model


The Corporate Crime Knowledge Model (display name: Corporate Crime EN v#) is a document classification model for English texts that predicts categories corresponding to businesses and companies crimes.
Corporate crime is commonly defined as:

crime committed by individuals within their legitimate occupations, for the benefit of their employing organization

In this Knowledge Model, the conceptual area covered by this term is expanded to include those crimes and wrongdoings that can easily affect or involve companies and business activities in general.

The model is designed to analyze a variety of texts such as:

  • News about corporate crimes from international newspapers and news agencies.
  • Press releases.
  • Articles from institutional sites.
  • Articles and abstracts from specialized legal sites.
  • Some types of legal documents, such us judicial opinions.

Category tree

Possible categories are:

01. Bankruptcy offences and corporate crime 
    01.01. Bankruptcy
    01.02. False social information
    01.03. Conflict of interest
    01.04. Unlawful appropriation
    01.05. Restraint of trade, anti-trust crime and unlawful competition
    01.06. Breach of contract
02. Tax fraud and evasion   
03. Financial and economic crime    
    03.01. Market abuse
    03.02. Financial crime
04. Corruption, abuse of office and crimes against the Public Administration    
05. Environmental crime 
    05.01. Pollution emissions and spills
    05.02. Illegal waste trafficking and disposal
06. Money laundering    
07. Occupational safety and health crime    
    07.01. Occupational safety crime
    07.02. Workplace violence
08. Fraud, forgery and counterfeiting   
09. Property crime  
    09.01. Extortion
    09.02. Usury
10. Intellectual property violations    
11. Violation of tendering contracts' codes 
99. Uncategorized


  • Bankruptcy offences and corporate crime: texts mentioning corporate crime, bankruptcy, false social information, conflict of interest, unlawful appropriation, restraint of trade, anti-trust crime, unlawful competition, breach of contract.
  • Tax fraud and evasion: texts mentioning tax evasion, undeclared earnings, tax frauds, and other tax-related offences.
  • Financial and economic crime: texts mentioning market abuse, insider trading, violation of security laws, terrorism financing, white-collar crimes, and other financial crimes not otherwise treated in a dedicated category.
  • Corruption, abuse of office and crimes against the Public Administration: texts mentioning corruption, bribery, misappropriation of public funds, exploitation of one’s official position for private gain, obstructing or evading justice, etc.
  • Environmental crime: crimes related to pollution, emissions and spills, and illegal waste trafficking and disposal.
  • Money laundering: texts mentioning injecting illicit money into an activity, transferring or smuggling illicit money, criminal activities in tax heavens, illicit financial cash flows and bank transactions, and money mules.
  • Occupational safety and health crime: texts mentioning occupational safety crimes as well as workplace violence.
  • Fraud, forgery and counterfeiting: texts mentioning fraud other than tax frauds, forgery, counterfeiting, pyramid schemes, fraud involving exploitation of personal information, cards cloning, illegal electrical connection, tampering of meters or documents, etc.; cyber or email fraud mentions are included but not expanded to cover types of cyber frauds, which are matter of cybercrime and not included in this category.
  • Property crime: texts mentioning extortion, racketing, and usury.
  • Intellectual property violations: texts mentioning violations to copyright and trademarks, patent infringement; cybercrimes involving intellectual property are included but not expanded to cover types of cyber-violations, which are matter of cybercrime and not included in this category.
  • Violation of tendering contracts' codes: texts mentioning tender and procurement rules violations, anti-competitive tender practices (collusive tendering, bid rigging, cover bidding, bid rotation, bid withdrawal) and public service contract violations.
  • Uncategorized is used to identify documents that the project cannot or is not designed to classify.

Output structure

The model output has the same structure as any other model and is affected by the functional properties of the workflow block.
The peculiar part of the output is the result of categorization, i.e. the categories array.


Considering the following text:

U.S. Attorneys» Southern District of New York» News» Press Releases
Department of Justice
U.S. Attorney's Office
Southern District of New York
Tuesday, September 8, 2015
Former Chairman And CEO Of Technology Start-Up Company KIT Digital, And Its Former Chief Financial Officer, Charged In Manhattan Federal Court
Preet Bharara, the United States Attorney for the Southern District of New York, Diego Rodriguez, the Assistant Director-in-Charge of the New York Field Office of the Federal Bureau of Investigation ("FBI"), and Philip R. Bartlett, Inspector-in-Charge of the New York Office of the U.S. Postal Inspection Service ("USPIS"), announced today the arrests of KALEIL ISAZA TUZMAN and ROBIN SMYTH. TUZMAN, the former chairman of the board of directors and chief executive officer of the technology start-up company KIT digital, was arrested yesterday in Colombia on market manipulation and accounting fraud charges. TUZMAN is being held in Colombia pending extradition proceedings. SMYTH, the former chief financial officer ("CFO") of KIT digital, a publicly traded company that was based in New York, New York, and Prague, Czech Republic, was arrested today in Australia on accounting fraud charges. SMYTH is being held in Australia pending extradition proceedings.

the output is:

"categories": [
        "frequency": 22.4,
        "hierarchy": [
            "Bankruptcy offences and corporate crime",
            "False social information"
        "id": "01.02.",
        "label": "False social information",
        "namespace": "corporate_crime_km_en",
        "positions": [...],
        "score": 26,
        "winner": true
        "frequency": 25.86,
        "hierarchy": [
            "Financial and economical crime",
            "Market abuse"
        "id": "03.01.",
        "label": "Market abuse",
        "namespace": "corporate_crime_km_en",
        "positions": [...],
        "score": 30,
        "winner": true
        "frequency": 51.72,
        "hierarchy": [
            "Fraud, forgery and counterfeiting"
        "id": "08.",
        "label": "Fraud, forgery and counterfeiting",
        "namespace": "corporate_crime_km_en",
        "positions": [...],
        "score": 60,
        "winner": true