Create an autonomous underwriting system which provides financing approval - ON-171

Preferred Disciplines: Computer science and business (Masters or PhD)
Company: Venbridge Ltd. 
Project Length: 6-12 months (1-2 units)
Desired start date: As soon as possible
Location: Toronto, ON
No. of Positions: 1
Preferences: None

About the Company: 

Venbridge provides debt financing for small and medium technology companies in Canada.  One of the common factors with these companies is that a majority of them lack assets and therefore do not qualify for traditional bank financing.  Venbridge provides financing based on a number of assets including tax credits (such as SR&ED), grants, cash flow, and revenue.

Project Description:

Venbridge would like to create a completely autonomous underwriting system that can provide debt financing to SME's without human intervention.  The system needs to be able to work on limited data sets, encompass machine learning to improve accuracy, gather disparate data such as financial statements, bank records, social information and sales forecasts, and provide an underwriting solution which is better than what humans can achieve.  I expect between 10 and 20 data sources to feed into the underwriting decision and pricing of the loan facility.  The data science, the AI and the machine learning will be the key to an effective system.

Research Objectives:

  • Determine relevant underwriting factors / data sources
  • Determine methodology for creating a credit score that is equal or more accurate than humans
  • Provide credit decision in real-time 

Methodology:

  • To be determined

Expertise and Skills Needed:

    • Machine learning
    • Data science
    • Computer programming
    • Statistics
    • Finance and accounting (useful but not necessary)

    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; or directly to Iman Yahyaie.
    Program: