Data-driven and process-aware workforce analytics

Modern information systems in today’s organisations record massive amount of event log data capturing the execution of day-to-day core processes within and across organisations. Mining these event log data to drive process analytics and knowledge discovery is known as process mining. To date various process mining techniques have been developed to help extract insights about the actual processes with the ultimate goal to organisations' workforce capability and capacity building.

As an important sub-field of process mining, organisational mining focuses on discovering organisational knowledge, including e.g. organisational structures and human resources relevant to the performance of an organisation's core processes, and continuously evolving organisational dynamics. In any organisation where humans play a dominant role, process-aware workfoce analytics helps managers gain a better understanding of the de facto grouping of human resources (e.g. team formation and dynamics) and their interactions thus to improve the related processes as well as the organisational performance towards the building of a healthy and sustainable workforce.

For more information about this research project, check out the world leading research initiative on eXplainable Analytics for Machine Intelligence (XAMI) at www.xami-lab.org

• Literature review on state-of-the-art approaches and techniques related to organisational mining.
• Design of new algorithms and techniques for workforce analytics based on study and application of various data mining techniques.
• Design of new algorithms and techniques for workforce analytics based on study and application of existing social network analysis techniques.
• Design of a systematic approach for actionable process improvement informed by the findings from organisational mining.
• Implementation of the new algorithms, techniques and approaches, visualisation of the results and finding, and evaluation using real event logs.

• New/improved methods and algorithms for organisational model mining built upon suitable data mining techniques.
• Novel approach and models for discovering, reasoning, and analysing (intra-)organisational and inter-organisational networks by leveraging existing social network analysis capabilities.
• New tools and visualisation of the discovered organisational networks.
• Knowledge discovery from process event logs for organisational improvement informed by management theories and principles.

• Familiarity with the fields of data mining (and preferably process mining and/or social network analysis).
• Problem-solving and critical thinking capabilities.
• Programming skills in Python.
• Academic writing skills.