Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Discovery Grants Program - Individual

University of Toronto

$69,000.00

Modern Waiting Time Management Using Business Analytics (Machine Learning and Artificial Intelligence, ML and AI) and its Applications in e.g., Healthcare

FY 2024-25

Summary
Modern Waiting Time Management Using Business Analytics, Machine Learning and Artificial Intelligence, (ML&AI) and its Applications in Healthcare This proposal extends my previous NSERC funded research on waiting time management to include modern applications of business analytics in waiting time management. As demonstrated by grants, awards, conferences, papers, and positions of highly qualified personnel trained, I have made substantial progress over the last 6 years. Queueing theory is focused on managing wait times. Important, though not yet sufficiently used, methodology in queueing theory is business analytics, including ML&AI. The ability to collect and analyze data opens new opportunities to implement business analytics in queues. The short-term goals of this proposal are to provide performance evaluation to a wide range of queues by integrating theoretical and analytics, data-driven, methods with ML&AI and to support companies in improving processes where congestion occurs. The long-term goals are to train HQP, promote the use of ML&AI among queueing theorists and practitioners, and offer prescriptive analytics for queues. These advancements can significantly improve resource usage, e.g., by improving employee shift scheduling, and enhance the quality of life for many individuals, e.g., by improving access to healthcare. My research includes four main projects (the data driven work will use sets I have and am obtaining from hospitals and justice systems). A) A tool to solve queueing systems: Several tools for solving queueing models exist. These tools solve models with closed form solutions or approximations. We will use ML&AI to solve a broader set of queues. We established the efficacy of our approach in simple settings and are extending it to non-stationary queues, multiple customer types, and queueing network. We will create training sets using closed form expressions (including accurate approximations) and numerical methods. B) Automating application dependent simulation of queues: Due to the inherent complexity of real queueing systems their analysis is often done via simulation. We combined process and queue mining with ML&AI to facilitate the automatic creation of simulations (patent pending). Our research will further support this method. C) Enhance data driven causality in queueing systems: Causal models are extremely important to management analytics. We formulated queueing causal models and use the G-computation to provide performance analysis of queues. We show that this method's accuracy is comparable to that of exact analysis! We will extend this framework and provide further intuition to its efficacy. D) Manage waits in practice: We are working with industry to improve access to service. E.g., in health care, policy often dictates maximum allowable wait times (e.g., the Canadian Triage and Acuity Scale). We will use data and ML&AI to improve access to care and justice at an equitable fashion.
Program
Discovery Grants Program - Individual
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data

As published

Application id
RGPIN-2024-05606
Name nom
Baron, Opher
Department département
Rotman School of Management
Organization id
31
Institution établissement
University of Toronto
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2024
Award amount
69000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
DISCOVERY RESEARCH
Group fr
RECHERCHE AXÉE SUR LA DÉCOUVERTE
Committee code
1509
Committee name en
Civil, Industrial and Systems Engineering
Committee name fr
Génie civil, industriel et des systèmes
Area of application code
900
Area of application group en
Commercial services
Area of application group fr
Services commerciaux
Area of application en
Commercial services
Area of application fr
Services commerciaux
Research subject code
1606
Research subject group en
Industrial engineering
Research subject group fr
Génie industriel
Research subject en
Operations management
Research subject fr
Gestion de la production
Field of research list names en
Not available
Field of research list names fr
Non disponible
Socioeconomic objective list names en
Not available
Socioeconomic objective list names fr
Non disponible
Application title
Modern Waiting Time Management Using Business Analytics (Machine Learning and Artificial Intelligence, ML and AI) and its Applications in e.g., Healthcare
Keywords
queueing theory; business analytics; machine learning; artificial inteligence; operations management; access to care; healthcare operations; simulation
Application summary
Modern Waiting Time Management Using Business Analytics, Machine Learning and Artificial Intelligence, (ML&AI) and its Applications in Healthcare This proposal extends my previous NSERC funded research on waiting time management to include modern applications of business analytics in waiting time management. As demonstrated by grants, awards, conferences, papers, and positions of highly qualified personnel trained, I have made substantial progress over the last 6 years. Queueing theory is focused on managing wait times. Important, though not yet sufficiently used, methodology in queueing theory is business analytics, including ML&AI. The ability to collect and analyze data opens new opportunities to implement business analytics in queues. The short-term goals of this proposal are to provide performance evaluation to a wide range of queues by integrating theoretical and analytics, data-driven, methods with ML&AI and to support companies in improving processes where congestion occurs. The long-term goals are to train HQP, promote the use of ML&AI among queueing theorists and practitioners, and offer prescriptive analytics for queues. These advancements can significantly improve resource usage, e.g., by improving employee shift scheduling, and enhance the quality of life for many individuals, e.g., by improving access to healthcare. My research includes four main projects (the data driven work will use sets I have and am obtaining from hospitals and justice systems). A) A tool to solve queueing systems: Several tools for solving queueing models exist. These tools solve models with closed form solutions or approximations. We will use ML&AI to solve a broader set of queues. We established the efficacy of our approach in simple settings and are extending it to non-stationary queues, multiple customer types, and queueing network. We will create training sets using closed form expressions (including accurate approximations) and numerical methods. B) Automating application dependent simulation of queues: Due to the inherent complexity of real queueing systems their analysis is often done via simulation. We combined process and queue mining with ML&AI to facilitate the automatic creation of simulations (patent pending). Our research will further support this method. C) Enhance data driven causality in queueing systems: Causal models are extremely important to management analytics. We formulated queueing causal models and use the G-computation to provide performance analysis of queues. We show that this method's accuracy is comparable to that of exact analysis! We will extend this framework and provide further intuition to its efficacy. D) Manage waits in practice: We are working with industry to improve access to service. E.g., in health care, policy often dictates maximum allowable wait times (e.g., the Canadian Triage and Acuity Scale). We will use data and ML&AI to improve access to care and justice at an equitable fashion.