Homepage

Brief Bio

Currently an Assistant Professor at the Institute of Science Tokyo, and a member of the Software Analytics Research Group with a keen interest in Machine Learning approaches to Software Engineering. My interests lie in structured approaches to modelling source code, program synthesis, understanding defect prediction, and the testing oracle problem. I received my PhD from University College London (UCL), where I worked under the supervision of Prof Earl T. Barr on improving project health by applying Machine Learning to problems from Software Engineering. Some of my projects are listed on this page.

In a long-forgotten age, I used to take photographs as well, I try to do so today as well. Some of these can be found here.

Bibliographic Profiles

Contact

Work

E-mail: partachi[at]sa[dot]comp[dot]isct[dot]ac[dot]jp

Personal

E-mail: me[at]partachi[dot]com

Curriculum Vitae

My CV can be found here.

Education

• PhD in Computer Science, Centre for Research on Evolution, Search and Testing, University College London; September 2016 – December 2020
  • PhD Thesis: Improving Software Project Health Using Machine Learning
  • Supervised by Prof Earl T. Barr
• BA in Computer Science, King's College, University of Cambridge; September 2013 – July 2016
  • BA Thesis: Deck building in Hearthstone Using a Genetic Algorithm.
  • Supervised by Dr Sean Holden

Projects

Doctoral Work

1. Aide-memoire: A tool to link issues and pull-requests in an online fashion by predicting which issues (PRs) relate to other PRs (issues). It makes use of a Mondrian Forest model that should be trained on a project before it can make predictions. It is composed of a backend (GitHub Link) and a Chrome plug-in to interface with the backend (GitHub Link)
2. POSIT: A tool that makes use of a CRF-biLSTM model to segment and tag text that mixes English and code snippets. It was trained on a combination of C code and StackOverflow. Project Page
3. Flexeme: A tool that untangles commits into atomic patches using graph kernel similarity and agglomerative clustering. It was validated on an artificial corpus of tangled commits for 9 C# projects. Project Page

Internship Projects

1. Graph-kernel-based detection of anomalous events in spatiotemporal data: anomalies are those points that stay closely together for abnormal lengths of time or disperse suddenly. This work was done as part of an internship at the National Institute of Informatics in Tokyo, JP, under the careful supervision of Asoc. Prof. Mahito Sugiyama.

Teaching Experience

TAing during the Post-doctoral Research

• Data Mining @ SOKENDAI (NII); October 2023 – January 2024
  • Leading the introduction to Graph Neural Networks lecture

TAing during the Doctoral Studies

• COMPM203 Verification and Validation; January 2020 – July 2020
  • Leading problem-based workshops, assisting with exam setting, and exam marking
• COMP103P Applied Software Development; January 2018 – April 2018
  • Laboratory Supervisor and Group Project Supervisor
• COMPM203 Verification and Validation; January 2018 – April 2018
  • Coursework writing and marking
• COMP213P Systems Engineering; October 2017 – April 2018
  • Group Project Supervisor

Reviews

Conferences

• Program Committee member for: Research and Experience at CAIN 2025, 2024, Research Track at ICSE 2026, FSE 2025, Artefact Evaluation at ICSE 2024, InteNSE 2023, Research Track at SANER 2023, 2022 Mining Challenge at MSR 2021.
• Reviewing for: NeurIPS 2025, ICLR 2025, AAAI 2025, ICLR 2024, ICML 2024, NeurIPS 2023
• Sub-reviewing for: ASE 2022, ISSTA 2021, SANER 2021, ICSE 2021, Registered Studies at ICSME 2020, ASE 2020, MSR 2020, FSE 2019, ISSTA 2019, ASE 2018, ECOOP 2018, ISSTA 2018, and MSR 2017.

Journals

• Editorial Board: Intellectus 2024–now
• Reviewing for: Intellectus 2024, TOSEM 2023, 2022, JSS 2022, 2021, EMSE 2021, and MTAP 2020.
• Sub-reviewing for: EAAI 2020, and TSE 2017