The Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD) is one of the longest established and leading international conferences in the areas of data mining and knowledge discovery. It provides an international peer-reviewed forum for researchers and industry practitioners who are addressing the problems to share their new ideas, original research results, and practical development experiences from all KDD-related areas, including data science, data mining, data warehousing, machine learning, artificial intelligence, databases, statistics, knowledge engineering, visualization, decision-making systems, and emerging applications.

Hosted in Wellington, New Zealand from 29 June – 2 July 2027, PAKDD 2027 continues this tradition with an engaging programme of keynote presentations, peer-reviewed research papers, workshops, tutorials, and a doctoral consortium. As a prestigious and highly selective conference, PAKDD brings together leading researchers and practitioners through invited talks and high-quality refereed research papers.

Everyone new to the field has many opportunities to learn about cutting-edge research by attending visionary keynote speeches, paper presentations, tutorials, and workshops.

Topics of relevance for the conference include, but are not limited to, the following.

== Theoretical Foundations ==

Mathematical, statistical, and information-theoretic foundations
Optimization methods for data mining and machine learning
Causal learning and causal inference
Representation learning
Non-IID learning and distribution shift
Domain adaptation and domain generalisation
Generalisation and out-of-distribution learning
Neuro-symbolic learning and reasoning
Generative modelling
Quantum machine learning
Foundations of trustworthy and responsible machine learning

== Learning Methods and Algorithms ==

Clustering, classification, pattern mining and association rules discovery
Supervised learning, semi-supervised learning, few-shot and zero-shot learning, active learning
Reinforcement learning and bandits
Transfer learning, federated learning
Anomaly detection, outlier detection
Learning in recommendation engines
Learning in streams and in time series
Learning on structured data, images, texts and multi-modal data
Online learning, model adaption
Graph mining and Graph NNs
Trustworthy Machine Learning
Fairness

== Data Processing for Learning ==

Dimensionality reduction, feature extraction, subspace construction
Data cleaning and preparation, data integration and summarization
Learning in real-time
Big data technologies
Information retrieval
Data/entity/event/relationship extraction
User interfaces and visual analytics

== Security, Privacy, Ethics, Information Integrity and Social Issues ==

Modeling credibility, trustworthiness, and reliability
Privacy-preserving data mining and privacy models
Model transparency, interpretability, and fairness
Misinformation detection, monitoring, and prevention
Social issues, such as health inequities, social development, and poverty

== Interdisciplinary Research on Data Science Applications ==

Social network/media analysis and dynamics, reputation, influence, trust, opinion mining, sentiment analysis, link prediction, and community detection
Symbiotic human-AI interaction, human-agent collaboration, socially interactive robots, and affective computing
Internet of Things, logistics management, network traffic and log analysis, and supply chain management
Business and financial data, computational advertising, customer relationship management, intrusion and fraud detection, and intelligent assistants
Urban computing, spatial data science and pervasive computing
Medical and public health applications, drug discovery, healthcare management, and epidemic monitoring and prevention
Methods for detecting and combating spamming, trolling, aggression, toxic online behaviors, bullying, hate speech, and low-quality and offensive content
Climate, ecological, and environmental science, and resilience and sustainability
Astronomy and astrophysics, genomics and bioinformatics, high energy physics, robotics, AI-assisted programming, and scientific data

== Other tracks ==

Papers with a strong applied or industrial focus are better suited to the Applied Data Science Track, whose call will be published separately. Work on large language models and agentic AI for data science is better suited to the Special Track on Large Language Models and Agentic AI, whose scope has been extended from large language models to large language models and agentic AI.