Evidently is an open-source ML and LLM observability framework. Evaluate, test, and monitor any AI-powered system or data pipeline. From tabular data to Gen AI. 100+ metrics.
Such as in regression models like Multi-task Lasso, where problems are solved jointly, would it be possible/is it planned to evaluate regression metrics jointly? i.e. We can see the effect of (single or multiple) x on multiple dimensions of y. This would mean allowing multiple target columns and multiple prediction columns for regressions.
Would be very much appreciated! A use-case would be a forecasting model in which many weeks are forecasted and you'd want to monitor short-term forecasting and long-term forecasting.
Such as in regression models like Multi-task Lasso, where problems are solved jointly, would it be possible/is it planned to evaluate regression metrics jointly? i.e. We can see the effect of (single or multiple) x on multiple dimensions of y. This would mean allowing multiple target columns and multiple prediction columns for regressions.