Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Idea to Innovation

University of Toronto

$124,300.00

ServiceMiner: Transforming process data into actionable insights

FY 2022-23

Summary
ServiceMiner is a tool that automates visualization, simulation, and optimization of service processes by mining transactional data. Specifically, it constructs data-driven simulation models directly from event-log and related data collected by common information systems (such as SAP). ServiceMiner enables users to improve processes, increase efficiency, reduce cost, and improve resource management. This technology, developed at the University of Toronto, can serve two types of customers: [1] process mining software companies that already provide some form of automated modeling based on transactional data, and [2] end-users (e.g., production facilities, call centers, and hospitals) that would use ServiceMiner in-house. For [1] customers, ServiceMiner provides significant enhancements to existing features of their systems. Both Celonis and Apromore, major players in the process mining space, strongly support our initiative. For [2] customers, ServiceMiner enables improved decision making and predictive capabilities on the fly, increased efficiency, optimized resource allocation, and improved customer service experience. The key ideas underlying ServiceMiner are in the process of being patented and the tool developed. In its current version, it has several building blocks. It automatically learns the structure of underlying processes (e.g., the manufacturing workflow in a production facility), and cluster cases (e.g., production orders) into types. This clustering provides a basis for learning the underlying distributions of arrivals and service durations, using machine learning and artificial intelligence methods. These building blocks form the basic components of the simulation model that is the output of the current version, allowing users to replay historical data to validate and verify its correctness in- and out-of-sample. ServiceMiner has been tested on several datasets and has done well in both descriptive and predictive tasks. This capability, to be further tested already makes ServiceMiner useful for both types of customers.
Program
Idea to Innovation
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data

As published

Application id
577517-2022
Name nom
Baron, Opher BO
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
2022
Competition year année de concours
2022
Award amount
124300
Program id
I2IPJ
Program name en
Idea to Innovation
Program name fr
De l'idée à l'innovation
Group en
RESEARCH PARTNERSHIPS
Group fr
PARTENARIATS DE RECHERCHE
Committee code
96
Committee name en
RPP Internal Decision Cttee
Committee name fr
Cté de décision interne - PPR
Area of application code
520
Area of application group en
Manufacturing processes and products
Area of application group fr
Procédés et produits industriels
Area of application en
Production and operations management
Area of application fr
Production et gestion des opérations
Research subject code
1601
Research subject group en
Industrial engineering
Research subject group fr
Génie industriel
Research subject en
Operations research and management science
Research subject fr
Recherche opérationnelle et science de la gestion
Installment
inst:1
Partie
1
Nb partie
1
Application title
ServiceMiner: Transforming process data into actionable insights
Application summary
ServiceMiner is a tool that automates visualization, simulation, and optimization of service processes by mining transactional data. Specifically, it constructs data-driven simulation models directly from event-log and related data collected by common information systems (such as SAP). ServiceMiner enables users to improve processes, increase efficiency, reduce cost, and improve resource management. This technology, developed at the University of Toronto, can serve two types of customers: [1] process mining software companies that already provide some form of automated modeling based on transactional data, and [2] end-users (e.g., production facilities, call centers, and hospitals) that would use ServiceMiner in-house. For [1] customers, ServiceMiner provides significant enhancements to existing features of their systems. Both Celonis and Apromore, major players in the process mining space, strongly support our initiative. For [2] customers, ServiceMiner enables improved decision making and predictive capabilities on the fly, increased efficiency, optimized resource allocation, and improved customer service experience. The key ideas underlying ServiceMiner are in the process of being patented and the tool developed. In its current version, it has several building blocks. It automatically learns the structure of underlying processes (e.g., the manufacturing workflow in a production facility), and cluster cases (e.g., production orders) into types. This clustering provides a basis for learning the underlying distributions of arrivals and service durations, using machine learning and artificial intelligence methods. These building blocks form the basic components of the simulation model that is the output of the current version, allowing users to replay historical data to validate and verify its correctness in- and out-of-sample. ServiceMiner has been tested on several datasets and has done well in both descriptive and predictive tasks. This capability, to be further tested already makes ServiceMiner useful for both types of customers.