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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Machine Learning (ML) can substantially improve the efficiency andeffectiveness of organizations and is widely used for different purposes withinSoftware Engineering. However, the selection and implementation of MLtechniques rely almost exclusively on accuracy criteria. Thus, fororganizations wishing to realize the benefits of ML investments, this narrowapproach ignores crucial considerations around the anticipated costs of the MLactivities across the ML lifecycle, while failing to account for the benefitsthat are likely to accrue from the proposed activity. We present findings foran approach that addresses this gap by enhancing the accuracy criterion withreturn on investment (ROI) considerations. Specifically, we analyze theperformance of the two state-of-the-art ML techniques: Random Forest andBidirectional Encoder Representations from Transformers (BERT), based onaccuracy and ROI for two publicly available data sets. Specifically, we comparedecision-making on requirements dependency extraction (i) exclusively based onaccuracy and (ii) extended to include ROI analysis. As a result, we proposerecommendations for selecting ML classification techniques based on the degreeof training data used. Our findings indicate that considering ROI as additionalcriteria can drastically influence ML selection when compared to decisionsbased on accuracy as the sole criterion

How Much Data Analytics is Enough? The ROI of Machine Learning Classification and its Application to Requirements Dependency Classification