SiMLQ: Transforming process data into actionable insights

SiMLQ is a process mining solution that uses event data and machine learning to automate the representation, analysis, and optimization of business processes. This enables better allocation of resources, increased productivity, and reduced costs in service systems.

SiMLQ helps answer complex process and organizational management questions such as: 

  • Customer Experience – What throughput, wait times, and other performance measures can be expected for each customer type? 
  • Efficiency, Cost-Savings, and Productivity – Where are the system bottlenecks how can they be relieved by smarter uses of existing resources? 
  • Prescription – What impacts can be expected from specific interventions in the system? 

Key Features

  • Automated network learning using a hybrid queue mining + ML approach (unique in the field) 
  • Effectively approximates system load when resource and queueing information are minimal and/or missing. This is often the case in cloud systems, hospitals, and public transportation systems.
  • Flexible intake of contextual attributes 
  • Enables digital twin simulation to allow comparative analysis of system changes 
  • Successfully tested on real-world hospital and cloud computing data 


  1. Service organizations need to identify inefficient processes to optimize resource allocation and reduce costs.
  2. Process data is complex: High volume, high velocity, and high variety.
  3. Current operations management and process optimization methods suffer from a lack of data-driven approaches to make evidence-based decisions.
  4. Poor processes have impact on quality and user experience. 

SiMLQ’s key strength is the ability to automatically prescribe data-driven recommendations to optimize processes, with minimal data and manual effort required. Existing tools in data mining and process simulation are either:

  1. Focused on descriptive and predictive analytics (e.g. process mining tools), while lacking prescriptive capabilities, or 
  2. Require extensive manual labour to tune the models (e.g. simulation tools)

SiMLQ bridges the gap between these two approaches, enabling:

  • Reduced data-to-simulation time, enabling faster intervention in hours vs. months
  • Ability to plan and optimize process and resource capacity with demand
  • Prescriptive analytics (not just prediction)

    The global big data and business analytics market was valued at 168.8 billion U.S. dollars in 2018 and is forecast to grow to 274.3 billion U.S. dollars by 2022, with a five-year compound annual growth rate (CAGR) of 13.2%. Because it is able to process many diverse sources of data, SiMLQ is applicable to a variety of service systems, including:

    • Healthcare (emergency departments, long term care homes)
    • Cloud computing (load planning, data services)
    • Retail (customer journey analytics, call centre workforce planning, supply chain) 
    • Logistics (scheduling, transportation coordination)


    • US and Canadian patent applications in prosecution (Nov 2023)
    • Seeking strategic licensees and collaborators with diverse data sets



    Related Resources

    VPRI Contact

    Laurent Moreno

    Innovations & Entrepreneurship Manager
    Innovations & Partnerships Office (IPO)
    (416) 946-0594