Analysis of Worker Locational Distribution

Location: CSIRO, Lindfield, NSW

Duration: 5 months

Keywords: Software development/engineering, Java or C++, Database programming MySQL, mathematics, data analytics and statistics

Project Background

Staybil is a social-impact start-up that seeks to understand and improve the impact of commuting on wide swaths of the Australian and global labour force. They are starting with the food service, retail, and hospitality sectors, which represent about 20% of the Australian workforce. Preliminary data shows that over 40% of workers at inner Sydney and inner western Sydney commute for over 40 minutes each way.

Scenario: A McDonalds worker commutes on a train past not one or two, but three other McDonalds, twice daily. It’s clearly inefficient and it’s not an isolated problem.

Staybil aims to use smart Google map and transport API data to show employers how they can optimise where their team members work based on where they live, driving lower turnover, lower training costs, lower commuter carbon, and more time living and working instead of commuting.

Staybil seek to supplement their business with an intern with skills in software, data, algorithm and engineering support. The PhD candidate needs to have strong software development skills in an applicable language such as C++ and Java.  The Intern doesn’t need to be a data scientist, but must have strong mathematics and statistical skills.

The core hypothesis: Can we drive a significant reduction in employee turnover costs (recruiting, training, etc) and associated environmental and societal impacts by 1) calculating and exposing more efficient locations of applicable workers than their existing residence/work locations, 2) determining and suggesting employee ‘swaps’ to applicable businesses, and 3) facilitating the business logistics and transactions required to complete the suggested swaps.

Research to be Conducted

  1. Using the data collected in pilot research at over a dozen McDonalds outlets in the Sydney area, create a data model that shows the worker locational distributions. The model should be flexible enough to accommodate future data collection. It requires a graphical mapping output for visualisation, most likely using the Google Maps API tools.
  2. Using the data model, create basic calculation routines to evaluate optimal trip times between each employee’s residence and work location. This will most likely use the existing transport API provided by SkedGo, a Sydney based transport analytics company.
  3. Create a matching algorithm that searches for best-fit suggestions to swap employees between best-fit outlets to improve the overall system efficiency (lowest cumulative commute time, best individual improvements, etc).

Skills Required

  • Software development/engineering, specifically Desktop/browser application software using Java or C++ or other relevant high level language.
  • Database programming such as MySQL
  • Good mathematics fundamentals
  • Familiarity with data analytics and statistics
  • Excellent communication skills
  • Excellent attention to detail and ability to follow best practices
  • Ability to create good documentation

Expected Outcomes

The desired outcome is a set of prototype tools that can be used to further test the hypothesis stated above. The tools will be critical in getting detailed feedback from stakeholders, potential customers, and potential investors. The data model can then be further refined and applied to other labour sectors.

The deliverables will be used to obtain key feedback from industry and government stakeholders, and potential investors. The core concept has already received keen interest from the NSW Data Analytics Center (DAC) and two independent venture capital firms.  This proof of concept prototype will be a key ingredient to future government as well as industry funding and resources.

Additional Details

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 50% 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 via the standard form available on the AMSI Intern website during the application process.
  • Internships are also subject to any requirements stipulated by the student’s and the academic mentor’s university.
Applications Close

16 October 2017

Reference:
INT – 0339