Research Resourcing Requirements using Machine Learning of Large Data Sets at a Major Engineering Company

Location: Sydney, NSW

Duration: 5 months

Project Background

TTW are a large engineering consultancy working on some of Australia’s largest and most prestigious projects. A major aspect of managing projects at such a scale is understanding the required resourcing across all projects within the company and predicting future resourcing requirements.

TTW have a large historical database of projects with various features, such as sectors (healthcare, commercial etc), timesheet data, invoicing etc. We seek to use this historical data to generate insights on future projects with the following aims:

  • Predict future resourcing requirements at scale across the company
    • Are we able to predict ahead of time (long term) likely periods where staff requirements do not meet staffing levels
  • Assist in project management –
    • Are we able to predict typical resourcing for a project to advice whether a project is running under/over budget
    • Can we prepare billing schedules in our fee proposals so that the client understands their financial commitment ahead of time

Research to be Conducted

Broadly speaking the task would be split into 5 segments:

  • Assessing the existing data to generate the feature set to be used in the ML model
  • Processing of the existing data
    The existing data exists on a database within our intranet. Processing and sorting of this data would be required prior to starting any modelling such that the data will yield the best results. Example of the cleaning are:

    • Truncating data for projects where small continued expenditure occurred for many months after practical completion
    • Grouping ‘main’ portions of the project, excluding elements such as variations to the design (paid as separate commissions) etc
  • Training of the ML model
    Using an appropriate portion of the chosen data set and features, train a machine learning model to predict likely future outcomes based various amounts of input data (i.e. partially completed data)
  • Validate the ML model
    Using another portion of the data set, run validation of the model to assess the reliability and accuracy
  • Conclude and report findings
    Highlight areas of success and areas which require further attention/work
    Disseminate the knowledge gained to representatives within TTW

Skills Required

If you’re a PhD student and meet some or all the below we want to hear from you. We strongly encourage women, indigenous and disadvantaged candidates to apply:

  • Expertise in data analysis
  • Mathematical knowledge suitable for implementation of ML, such as linear algebra
  • Demonstrable experience using ML as regression analysis
  • Experience using existing data sets for training ML models including selecting of features and cleaning of data
  • Use of Python, Matlab or ML.Net for implementing Machine Learning

Expected Outcomes

The following outcomes are expected from this body of work:

  • Production of a validated ML model suitable for prediction of the following:
    • Companywide long-term resourcing requirements – this would need to be split by ‘staff type’ and ‘level’ (such as Senior Structural Engineers, Graduate Civil Engineers, Structural Drafters etc)
    • Predicted monthly staffing requirements for projects
    • Generation of billing schedules at the start of the project based on information contained within the fee proposal
      The model should be able to accept a varying degree of input parameters with more parameters ideally yielding more accurate predictions
  • Interaction and knowledge share with representatives at TTW
    • Production of a report highlighting the following:
    • Use of the ML model and system
    • Areas which require further work

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 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.

Applications Close

15 January 2020


APR – 1207