Time Series Visualizations

The following tables and options are available for Time Series visualizations.

Models table

Displays target series name(s), model types, and several measures of model fit. In the Actions column, click on the dot column and select View to see more detailed information on the model for a particular series.

Temporal Information Summary table

Provides information about the structure of the time series analyzed, including the specified time field, the time point increment, first and last times, and the number of unique time points.

Model Information table

For each target series, displays the type of model fitted, the number of predictors (if any), and a variety of standard measures of model fit for times series analyses. Measures included where smaller is better are Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Root Mean Squared Percent Error (RMSPE), Mean Absolute Error (MAE), Mean Absolute Percent Error (MAPE), (Maximum Absolute Error (MAXAE), Maximum Absolute Percent Error (MAXAPE), Akaike Information Criterion (AIC), and Normalized Bayesian Information Criterion (BIC). Measures included where larger is better are R2 and Stationary R2. The Ljung-Box Q statistic is also displayed, along with its degrees of freedom and significance value for testing the null hypothesis that the residuals from the fitted model are random noise.


A pair of correlograms, or autocorrelation plots, is shown for each target, displaying the autocorrelation function (ACF) and partial autocorrelation function (PACF) of the noise residuals versus the time lags. Confidence intervals are shown as highlight across each chart.

Parameter Estimates table

For each target series, a table containing the name of the target series, identifying each of the parameters fitted, along with the parameter coefficient estimate, its standard error, a t statistic (the coefficient estimate divided by its standard error) and significance value.

Next steps

Like your visualization? Why not deploy it? For more information, see Deploy a model.