Data Driven Anomaly Detection

Location: Melbourne, VIC

Duration: 4-6 months

Project Background

Telstra has a strong customer base associated to various products. These customers consist of employees, contractors and vendors, with the latter two categories classified as non-direct. Many of the non-direct group comes from Services companies, with longer term contracts, where the workforce keeps changing and the payments process becomes complicated adhering to various clauses of the contracts. The management believes more can be done in this regard to make the process more value-driven for all parties to get their optimal share. There is a large amount of data collected on various aspects of this engagement. The intern will work closely with multiple teams to identify avenues of improvements based on data.

Research to be Conducted

Telstra has embarked in a journey to improve their management insights on multiple aspects of customer engagement. Parts of this work involves building data-driven taxonomies, ontologies, do automated data segmentation, identify anomalies and convert them into actionable insights that could be disseminated to enhance current processes. This research looks at data that is both structured and unstructured and apply statistical modelling to pin-point specific instances which contribute to bad customer experience, fraudulent or risky transactions and determining associated root-cause.

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:

  • Data Science, Machine Learning, Text analytics/NLP and AI techniques
  • R/Python/Java/Scala programming
  • Ontology building, topic modelling, Self-organising maps, and other clustering techniques
  • Some knowledge of anomalies and fraud detection methods would be a plus

Expected Outcomes

The Intern is expected to collaborate with Telstra staff and provide data science capability. The project is expected to provide predictive models, anomaly detection methods and develop a system for AI driven decisions to pin-point good practices, anomalies, and fraud or high-risk behaviours.

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

22 January 2020


APR – 1179