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

Machine learning models may involve decision boundaries that change over timedue to updates to rules and regulations, such as in loan approvals or claimsmanagement. However, in such scenarios, it may take time for sufficienttraining data to accumulate in order to retrain the model to reflect the newdecision boundaries. While work has been done to reinforce existing decisionboundaries, very little has been done to cover these scenarios where decisionboundaries of the ML models should change in order to reflect new rules. Inthis paper, we focus on user-provided feedback rules as a way to expedite theML models update process, and we formally introduce the problem ofpre-processing training data to edit an ML model in response to feedback rulessuch that once the model is retrained on the pre-processed data, its decisionboundaries align more closely with the rules. To solve this problem, we proposea novel data augmentation method, the Feedback Rule-Based OversamplingTechnique. Extensive experiments using different ML models and real worlddatasets demonstrate the effectiveness of the method, in particular the benefitof augmentation and the ability to handle many feedback rules.

FROTE: Feedback Rule-Driven Oversampling for Editing Models