Novel Metric LxCIM for Binary Classifier Performance
Analysis
This research introduces LxCIM, a new metric designed to evaluate the performance of binary classifiers. The invariance to local class exchanges is a potentially valuable property, offering a more robust evaluation in certain scenarios.
Key Takeaways
- •LxCIM is a new metric for evaluating binary classifiers.
- •The metric is invariant to local class exchanges.
- •The paper is available on ArXiv.
Reference
“LxcIM is a new rank-based binary classifier performance metric invariant to local exchange of classes.”