Preferred Label : Performance Metrics;
EFMI definition : In the context of AI quantitative or qualitative measures that can be used to assess
the ability of a model to produce the desired output for a given task. The choice
of the metrics depends on the specific task and the model objectives. Examples of
quantitative metrics include accuracy, precision, sensitivity (recall), specificity,
F1-score, and Area under the Receiver Operating Characteristic curve (AUC-ROC). Qualitative
measures may involve heatmap evaluations or visual interpretations. These metrics
enable systematic evaluation, comparison, and refinement of models, and aid in the
assessment of whether the model meets its intended objectives.; Source: Adapted from International Organization for Standardization. (2020). Software
and systems engineering — Software testing — Part 11: Guidelines on the testing of
AI-based systems (ISO/IEC TR 29119-11: 2020). https://www.iso.org/standard/79016.html;
Origin ID : 300245;
Currated CISMeF NLP mapping
In the context of AI quantitative or qualitative measures that can be used to assess
the ability of a model to produce the desired output for a given task. The choice
of the metrics depends on the specific task and the model objectives. Examples of
quantitative metrics include accuracy, precision, sensitivity (recall), specificity,
F1-score, and Area under the Receiver Operating Characteristic curve (AUC-ROC). Qualitative
measures may involve heatmap evaluations or visual interpretations. These metrics
enable systematic evaluation, comparison, and refinement of models, and aid in the
assessment of whether the model meets its intended objectives.
Source: Adapted from International Organization for Standardization. (2020). Software
and systems engineering — Software testing — Part 11: Guidelines on the testing of
AI-based systems (ISO/IEC TR 29119-11: 2020). https://www.iso.org/standard/79016.html
