As machine learning systems become increasingly integrated into high-stakes decision-making processes, ensuring fairness in algorithmic outcomes has become a critical concern. Methods to mitigate bias typically fall into three categories: pre-processing, in-processing, and post-processing. While significant attention has been devoted to the latter two, pre-processing methods, which operate at the data level and offer advantages such as model-agnosticism and improved privacy compliance, have received comparatively less focus and lack standardised evaluation tools. In this work, we introduce FairPrep, an extensible and modular benchmarking framework designed to evaluate fairness-aware pre-processing techniques on tabular datasets. Built on the AIF360 platform, FairPrep allows seamless integration of datasets, fairness interventions, and predictive models. It features a batch-processing interface that enables efficient experimentation and automatic reporting of fairness and utility metrics. By offering standardised pipelines and supporting reproducible evaluations, FairPrep fills a critical gap in the fairness benchmarking landscape and provides a practical foundation for advancing data-level fairness research.

Current malaria elimination targets must withstand a colossal challenge-resistance to the current gold standard antimalarial drug, namely artemisinin derivatives. If artemisinin resistance significantly expands to Africa or India, cases and malaria-related deaths are set to increase substantially. Spatial information on the changing levels of artemisinin resistance in Southeast Asia is therefore critical for health organisations to prioritise malaria control measures, but available data on artemisinin resistance are sparse. We use a comprehensive database from the WorldWide Antimalarial Resistance Network on the prevalence of non-synonymous mutations in the Kelch 13 (K13) gene, which are known to be associated with artemisinin resistance, and a Bayesian geostatistical model to produce spatio-temporal predictions of artemisinin resistance. Our maps of estimated prevalence show an expansion of the K13 mutation across the Greater Mekong Subregion from 2000 to 2022. Moreover, the period between 2010 and 2015 demonstrated the most spatial change across the region. Our model and maps provide important insights into the spatial and temporal trends of artemisinin resistance in a way that is not possible using data alone, thereby enabling improved spatial decision support systems on an unprecedented fine-scale spatial resolution. By predicting for the first time spatio-temporal patterns and extents of artemisinin resistance at the subcontinent level, this study provides critical information for supporting malaria elimination goals in Southeast Asia.

Item Response Theory (IRT) has been proposed within the field of Educational Psychometrics to assess student ability as well as test question difficulty and discrimination power. More recently, IRT has been applied to evaluate machine learning algorithm performance on a single classification dataset, where the student is now an algorithm, and the test question is an observation to be classified by the algorithm. In this paper we present a modified IRT-based framework for evaluating a portfolio of algorithms across a repository of datasets, while simultaneously eliciting a richer suite of characteristics - such as algorithm consistency and anomalousness - that describe important aspects of algorithm performance. These characteristics arise from a novel inversion and reinterpretation of the traditional IRT model without requiring additional dataset feature computations. We test this framework on algorithm portfolios for a wide range of applications, demonstrating the broad applicability of this method as an insightful algorithm evaluation tool. Furthermore, the explainable nature of IRT parameters yield an increased understanding of algorithm portfolios.