Red X iconGreen tick iconYellow tick icon
Sherlock Licorish imageBSc(UoG), MSc, PhD(AUT)
Associate Professor

Room 3.41, Otago Business School
Tel +64 3 479 8319
Linkedin Sherlock Licorish

Background and interests

Associate Professor Sherlock Licorish's current research focuses on:

  • Modelling the software development process and evaluating the use of software methodologies, and particularly agile approaches.
    Modelling sample paper (PDF)
  • Exploring and evaluating software teams' behaviour and performance under various conditions, or in addressing various forms of software activities (e.g. resolving defects or building new features, gathering software requirements, or performing software maintenance tasks).
    Behaviour sample paper (PDF)
  • The development and provision of software tools to aid software developers and enhance end-users' involvement in the feedback processes. Associate Professor Licorish is also interested in topics considered under market-driven (and crowd-sourced) requirements engineering.
    Software tools sample paper (PDF)
    Crowdsourcing sample paper (PDF)
  • Empirical software engineering and software analytics, covering software code quality and fault detection and repair, static analysis tools, global software development, open source software (OSS) development and virtual communities.
    Global development sample paper (PDF)
    OSS sample paper (PDF)

Associate Professor Licorish's analytics research involves the use of data mining, data visualization, statistical analysis and other quantitative methods (e.g. social network analysis, linguistic and sentiment analysis, natural language processing (NLP) and probabilistic modelling techniques).

He has also used qualitative methods in his research, including qualitative forms of content analysis and dilemma analysis. These techniques (both quantitative and qualitative) are often applied to large repositories and software artefacts.

Associate Professor Licorish serves as a reviewer for several top conferences and journals.

Associate Professor Licorish is involved in the research group:

Information Systems and Software Engineering



Associate Professor Licorish has been the recipient of a Supervisor Award.

Currently supervising

  • Pascal Omondiagbe
  • Lakmal Vithanage
  • Chathrie Wimalasooriya
  • Elijah Zoldouarrati

Currently co-supervising

  • Adriaan Lotter

Completed supervisions

  • Fathima Nuzla Ismail (PhD)
  • Saurabh Malgaonkar (PhD)
  • Elijah Zolduoarrati (MSc)
  • Adriaan Lotter (MSc)
  • Mihir Kumar Jha (MSc)
  • Phonephasouk Volabouth (MSc)
  • Pascal Omondiagbe (MSc)
  • Chan Won Lee (MSc)
  • Swetha Keertipati (MSc)
  • Smitha Keertipati (MSc)
  • Elijah Zolduoarrati (Hons)
  • Mike Huang (Hons)
  • Sarah Meldrum (Hons)
  • Georgia Greenheld (Hons)
  • Tavita Su'a (Hons)


Wimalasooriya, C., Licorish, S. A., Alencar da Costa, D., & MacDonell, S. G. (2024). Just-in-Time crash prediction for mobile apps. Empirical Software Engineering, 29, 68. doi: 10.1007/s10664-024-10455-7 Journal - Research Article

Omondiagbe, O. P., Licorish, S. A., & MacDonell, S. G. (2024). Improving transfer learning for software cross-project defect prediction. Applied Intelligence, 24, 5593-5616. doi: 10.1007/s10489-024-05459-1 Journal - Research Article

Ismail, F. N., Sengupta, A., Woodford, B. J., & Licorish, S. A. (2024). A comparison of one-class versus two-class machine learning models for wildfire prediction in California. In D. Benavides-Prado, S. Erfani, P. Fournier-Viger, Y. L. Boo & Y. S. Koh (Eds.), Data Science and Machine Learning: Proceedings of the 21st Australasian Conference, AusDM 2023 [Communications in Computer and Information Science 1943]. (pp. 239-253). Singapore: Springer. doi: 10.1007/978-981-99-8696-5_17 Conference Contribution - Published proceedings: Full paper

Licorish, S. A., Alencar da Costa, D., Zolduoarrati, E., & Grattan, N. (2024). Relating team atmosphere and group dynamics to student software development teams’ performance. Information & Software Technology, 167, 107377. doi: 10.1016/j.infsof.2023.107377 Journal - Research Article

Omondiagbe, O. P., Lilburne, L. R., Licorish, S. A., & MacDonell, S. G. (2023). Soil texture prediction with automated deep convolutional neural networks and population-based learning. Geoderma, 436, 116521. doi: 10.1016/j.geoderma.2023.116521 Journal - Research Article

Back to top