Accuracy evaluation metric
Last updated: Jan 30, 2025
The accuracy metric measures how correct your model predictions are by calculating the proportion of correct results among the total number of results.
Metric details
Accuracy is a quality evaluation metric that measures the quality of the performance of binary and multiclass classification machine learning models in watsonx.governance.
Scope
The accuracy metric evaluates machine learning models only.
- Types of AI assets: Machine learning models
- Machine learning problem type:
- Binary classification
- Multiclass classification
Scores and values
The accuracy metric score indicates the proportion of correct predictions that are made by your model when compared to the total number of predictions. Higher scores indicate that more correct predictions are made.
- Range of values: 0.0-1.0
- Best possible score: 1.0
- Chart values: Last value in the timeframe
- Ratios:
- At 0: no correct predictions
- Over 0: indicates increasing accuracy with more correct predictions
Settings
Default threshold: Lower limit = 80%
Do the math
Accuracy is calculated with the following formula:
- TP = True positives
- TN = True negatives
- FP = False positives
- FN = False negatives
Parent topic: Evaluation metrics
Was the topic helpful?
0/1000