Automated business content classification - BC-400

Preferred Disciplines: Computer science, Mathematics, Data scientist (Masters or PhD)
Project length: 4-6 months (1 unit)
Approx. start date: As soon as possible
Location: Vancouver, BC
No. of Positions: 1
Preferences: None
Company: VersaFile Inc

About Company:

VersaFile Inc. aims to invent, build, and deliver Content, Process, and Automation Solutions that are easy to use, functionally rich, and quick to value so that our customers can better their business. Basically, our business revolves completely around helping companies organize, manage and streamline document management practices for their business and compliance requirements.

Summary of Project:

Business documents almost always reference multiple topics and may contain large volumes of text. Current Machine Learning tools/algorithms are not effective in classifying multi-faceted documents without very specific context being applied. For most organizations that have large repositories (ie File Shares; SharePoint in 10’s of TB’s) of content, the professional labour required to apply context to the content would take hundreds if not thousands of hours. This is just not feasible, so an automated solution is required for one-time clean-up activities as well as ongoing classification of new incoming documents. VersaFile needs help to research options, tools, algorithms and methods to breakdown the elements and topics of a document, automatically enhance it with metadata and use logic to determine which business record category best applies to the overall document.

Research Objectives/Sub-Objectives:

  • Develop an algorithm to breakdown document elements
  • Metadata extraction and business document classification


    • Can be discussed with the researcher

    Expertise and Skills Needed:

    • Proficiency in a programming language
    • Natural language processing
    • Machine learning

    For more info or to apply to this applied research position, please

    1. Check your eligibility and find more information about open projects.
    2. Interested students need to get the approval from their supervisor and send their CV along with a link to their supervisor’s university webpage by applying through the webform