English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Data science projects often involve various machine learning (ML) methodsthat depend on data, code, and models. One of the key activities in theseprojects is the selection of a model or algorithm that is appropriate for thedata analysis at hand. ML model selection depends on several factors, whichinclude data-related attributes such as sample size, functional requirementssuch as the prediction algorithm type, and non-functional requirements such asperformance and bias. However, the factors that influence such selection areoften not well understood and explicitly represented. This paper describesongoing work on extending an adaptive variability-aware model selection methodwith bias detection in ML projects. The method involves: (i) modeling thevariability of the factors that affect model selection using feature modelsbased on heuristics proposed in the literature; (ii) instantiating ourvariability model with added features related to bias (e.g., bias-relatedmetrics); and (iii) conducting experiments that illustrate the method in aspecific case study to illustrate our approach based on a heart failureprediction project. The proposed approach aims to advance the state of the artby making explicit factors that influence model selection, particularly thoserelated to bias, as well as their interactions. The provided representationscan transform model selection in ML projects into a non ad hoc, adaptive, andexplainable process.

Extending Variability-Aware Model Selection with Bias Detection in Machine Learning Projects