DeepLearn Tools
Menu

ML Metrics Calculators

If 1% of transactions are fraud, a model that always answers "not fraud" scores 99% accuracy and catches nothing. That is why these calculators report F1, AUC, MCC and the rest, and show every step so you can check them against your own code. Paste in your counts or your predictions, read the intermediate values — precision, recall, true and false positives — and see which metric your data actually justifies reporting.

Nothing here yet.

The first ml metrics tools are on their way. In the meantime, browse every tool or start from the homepage.