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

The accuracy of binary classification systems is defined as the proportion ofcorrect predictions - both positive and negative - made by a classificationmodel or computational algorithm. A value between 0 (no accuracy) and 1(perfect accuracy), the accuracy of a classification model is dependent onseveral factors, notably: the classification rule or algorithm used, theintrinsic characteristics of the tool used to do the classification, and therelative frequency of the elements being classified. Several accuracy metricsexist, each with its own advantages in different classification scenarios. Inthis manuscript, we show that relative to a perfect accuracy of 1, the positiveprevalence threshold ($\phi_e$), a critical point of maximum curvature in theprecision-prevalence curve, bounds the $F{_{\beta}}$ score between 1 and1.8/1.5/1.2 for $\beta$ values of 0.5/1.0/2.0, respectively; the $F_1$ scorebetween 1 and 1.5, and the Fowlkes-Mallows Index (FM) between 1 and $\sqrt{2}\approx 1.414$. We likewise describe a novel $negative$ prevalence threshold($\phi_n$), the level of sharpest curvature for the negative predictivevalue-prevalence curve, such that $\phi_n$ $>$ $\phi_e$. The area between boththese thresholds bounds the Matthews Correlation Coefficient (MCC) between$\sqrt{2}/2$ and $\sqrt{2}$. Conversely, the ratio of the maximum possibleaccuracy to that at any point below the prevalence threshold, $\phi_e$, goes toinfinity with decreasing prevalence. Though applications are numerous, theideas herein discussed may be used in computational complexity theory,artificial intelligence, and medical screening, amongst others. Wherecomputational time is a limiting resource, attaining the prevalence thresholdin binary classification systems may be sufficient to yield levels of accuracycomparable to that under maximum prevalence.

Prevalence Threshold and bounds in the Accuracy of Binary Classification Systems