Balanced accuracy
Balanced accuracy is the average of recall values calculated separately for each class, giving each class equal weight regardless of its frequency.
Ensemble Methods for Machine Learning
Balanced accuracy is the average of recall values computed separately for each class.
- How it is used
- Uses balanced accuracy to compare classifiers and score permutation feature importance when class distributions are uneven.
- How deep it goes
- Defines the metric’s class-balancing purpose and demonstrates library scoring, but does not derive its mathematical formula.
- Examples
- Demonstrates imbalanced customer classification, multiclass digit classification, ensemble comparisons, and permutation importance.
- What you can do after
- Evaluate imbalanced classifiers and feature importance with scikit-learn’s balanced_accuracy_score or balanced_accuracy scoring.
Read how Ensemble Methods for Machine Learning explains balanced accuracy →
Evolutionary Deep Learning: Genetic algorithms and neural networks
Balanced accuracy is the average of per-class recall values, giving equal weight to each class regardless of its frequency.
- How it is used
- Scores image-classification genomes when random batches may produce biased class distributions.
- How deep it goes
- Defines the balancing rationale and demonstrates a complete scoring call, but does not derive the metric mathematically.
- Examples
- Uses MNIST-like 28×28 images, random batches of 256, and NEAT genome predictions.
- What you can do after
- Apply it via scikit-learn to assign balanced classification fitness to a genome.
Related concepts
- accuracycontrasts with · Accuracy is the degree to which an output, prediction, or measurement agrees with a correct or reference outcome under a specified criterion.
- class imbalanceaddresses · Class imbalance is a condition in a classification dataset where classes have substantially unequal numbers of examples.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.