Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Engage Grants Program

University of Waterloo

$24,900.00

Using natural language processing to optimize the efficiency of long-form content review by compliance officers

EF 2016-17

Résumé
Financial advisors are constantly under pressure to grow and sustain their business practice using marketing techniques despite being in a highly regulated industry. For example, the recent rise of the Robo-Advisor is shifting the way in which financial advisors communicate with their clients. In order to scale these demands, many financial advisors are turning to the use of digital marketing techniques. This trend, combined with the trend of increasing regulatory requirements for advisors impedes financial advisors' ability to grow and sustain their business. This is due to the fact that all content classified, as ""advertising content"" must undergo reviewby a compliance department before it is published. The criteria used in evaluating content include determining whether it mentions company names in a context that may be interpreted as endorsement, and determining whether the writing style is appropriate in terms of formality and sentiment. Veriday Inc. has a platform supporting the process of content reviewing by compliance officers. At present, the process is entirely manual, and is therefore time-consuming. The goal of the proposed project is to partially automate this process by developing an algorithm that would identify instances of biased mentions of company or product names and would measure the sentiment of the overall document by assigning numerical scores in objective, positive and negative categories. This information will be used by compliance officers in identifying content that has high risk of non-compliance, so that they can plan and prioritize their work better.
Programme
Engage Grants Program
Emplacement
Ontario, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data

Tel que publié

Application id
499864-2016
Name nom
Vechtomova, Olga
Department département
Management Sciences
Organization id
33
Institution établissement
University of Waterloo
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2016
Competition year année de concours
2016
Award amount
24900
Program id
EGP
Program name en
Engage Grants Program
Program name fr
Programme de subventions d'engagement partenariat
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
1553
Committee name en
Ontario Internal Decision Committee
Committee name fr
Comité de décision interne pour l'Ontario
Area of application code
800
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Information and communication services
Area of application fr
Services d'information et de télécommunications
Research subject code
2710
Research subject group en
Information technology
Research subject group fr
Technologie de l'information
Research subject en
Information systems design
Research subject fr
Conception de systèmes d'information
Partie
1
Nb partie
1
Application title
Using natural language processing to optimize the efficiency of long-form content review by compliance officers
Keyword
NSERC
Application summary
Financial advisors are constantly under pressure to grow and sustain their business practice using marketing techniques despite being in a highly regulated industry. For example, the recent rise of the Robo-Advisor is shifting the way in which financial advisors communicate with their clients. In order to scale these demands, many financial advisors are turning to the use of digital marketing techniques. This trend, combined with the trend of increasing regulatory requirements for advisors impedes financial advisors' ability to grow and sustain their business. This is due to the fact that all content classified, as ""advertising content"" must undergo reviewby a compliance department before it is published. The criteria used in evaluating content include determining whether it mentions company names in a context that may be interpreted as endorsement, and determining whether the writing style is appropriate in terms of formality and sentiment. Veriday Inc. has a platform supporting the process of content reviewing by compliance officers. At present, the process is entirely manual, and is therefore time-consuming. The goal of the proposed project is to partially automate this process by developing an algorithm that would identify instances of biased mentions of company or product names and would measure the sentiment of the overall document by assigning numerical scores in objective, positive and negative categories. This information will be used by compliance officers in identifying content that has high risk of non-compliance, so that they can plan and prioritize their work better.