DATA ANALYTICS & PROCESS OPTIMISATION FOR RESOURCE ALLOCATION
Location: Docklands, VIC
Duration: 5 months
Keywords: optimisation, data mining and analytics, programming, machine learning
In any large organization, allocation of resources remains a challenging problem. This becomes more challenging in highly variable environments that span diverse operations and markets. This problem isn’t constrained to human resources, but extends to include other project initiation, management and delivery resourcing tasks, as well as general business practices that require navigation of information systems.
In a climate that demands ever increasing flexibility, there is also the potential to enable greater flexibility across the workplace by capturing under-utilised skill sets and resources. To achieve this capability, greater efficiency is required in allocation strategies as well as trend analysis, pattern identification and anomaly detection.
This requires more effective data capture and a deeper understanding of the content. Emerging capabilities across data analytics, machine learning and the internet of things (IoT) are presenting opportunities to more easily measure, monitor, assess and adjust system performance by integrating data from diverse sources. Additionally, machine learning applied to large and diverse data sets is enabling efficiency gains and predictive modelling for maintenance and resource scheduling.
Research to be Conducted
The organisation is seeking expertise in system modelling, data integration and machine learning, with a view to optimising system performance through the mining and analysis of existing data sets as well as the incorporation of data/information from external data sources. Principles taken from crowd-sourcing and task sharing may be explored to refine a framework within which emerging technologies are applied to balance project needs, resource availability and expertise matching. This may draw upon machine learning techniques, data mining and analytics, as well as scheduling and operations management strategies to develop a recommending system for resource allocation. Where possible this information would form part of a feedback mechanism to continuously (or at least periodically) adapt system operation.
This expertise is necessary to improve industry practice for process management and resource allocation by integrating additional and novel data streams to better understand the operating environment, requirements and potential efficiency gains. This requires the exploration and consolidation of emerging technological capabilities to address conventional system operations.
Key objectives from the research include:
- Collection, aggregation and analysis of disparate data.
- System modelling and algorithm development for event detection and/or process optimisation.
- Integration of outcomes into a suitable end-user platform or interface
For this project, we are looking for PhD students with:
Programming skills and algorithm development, particularly in relevant areas of data analytics and machine learning, as well as information systems analysis/design.
Specific development platforms are unspecified at this stage and can be explored as the project demands and the expertise of candidate dictates.
The expected outcome of the project will be a software model demonstrating the ability to source relevant information from a variety of sources, accurately capture up to date information, identify patterns/anomalies and optimise recommendations/allocations according to given criteria. The potential for additional gains resulting from the integration of independent data streams as well as predictive modelling of system parameters and anomaly detection are also to be explored. The system may be partially or fully integrated into an existing system (internally or client linked) as resources permit.
The final presentation should demonstrate the functionality of the system as a proof of concept and reveal the inherent challenges and potential complexities in delivering such a capability. Insight into the suitability of associated development platforms and level of expertise required in delivering a robust industry solution is also anticipated.
The intern will receive $3,000 per month of the internship, usually in the form of stipend payments.
It is expected that the intern will primarily undertake this research project during regular business hours, spending at least 80% of their time on-site with the industry partner. The intern will be expected to maintain contact with their academic mentor throughout the internship either through face-to-face or phone meetings as appropriate.
The intern and their academic mentor will have the opportunity to negotiate the project’s scope, milestones and timeline during the project planning stage.
To participate in the AMSI Intern program, all applicants must satisfy the following criteria:
- Be a PhD student currently enrolled at an Australian University.
- PhD candidature must be confirmed.
- Applicants must have the written approval of their Principal Supervisor to undertake the internship. This approval must be submitted at the time of application.
- Internships are also subject to any requirements stipulated by the student’s and the academic mentor’s university.
27 October 2017
INT – 0357