Product FAQs

What data types does Eizen Observability support?

Eizen Observability supports tabular/structured data types (strings, floats, booleans, etc), as well as embedding support for NLP, Image, and other unstructured data types.

What model types does Eizen Observability support?

Eizen Observability supports Binary Classification, Multi-Class Classification, Time Series, Prediction and Detection.

What evaluation metrics does EM Observability support?

Eizen Observability supports Accuracy, Recall, Precision, F- 1 Score, False Positive Rate(FPR) and False Negative Rate(FNR), Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), R-Squared (Coefficient of Determination), Adjusted R-Squared and Mean Absolute Percentage Error (MAPE).

How does Eizen Observability calculate data drift?

Eizen Observability calculates the data drift by comparing the production data with a baseline dataset and notify you when the drift is detected.

How does Eizen Observability log our model inferences?

Eizen Observability provides a module to integrate with your model APIs to get the model inferences and log in the interface.