# Series Insights (clustering)

> Series Insights (clustering) - Available for clustering projects, the Series Insights tab provides
> series clustering information in both charted and tabular format.

This Markdown file sits beside the HTML page at the same path (with a `.md` suffix). It summarizes the topic and lists links for tools and LLM context.

Companion generated at `2026-04-24T16:03:56.587935+00:00` (UTC).

## Primary page

- [Series Insights (clustering)](https://docs.datarobot.com/en/docs/classic-ui/modeling/analyze-models/evaluate/series-insights-classic.html): Full documentation for this topic (HTML).

## Sections on this page

- [Use Series Insights](https://docs.datarobot.com/en/docs/classic-ui/modeling/analyze-models/evaluate/series-insights-classic.html#use-series-insights): In-page section heading.
- [Histogram](https://docs.datarobot.com/en/docs/classic-ui/modeling/analyze-models/evaluate/series-insights-classic.html#histogram): In-page section heading.
- [Table view](https://docs.datarobot.com/en/docs/classic-ui/modeling/analyze-models/evaluate/series-insights-classic.html#table-view): In-page section heading.

## Related documentation

- [Classic UI documentation](https://docs.datarobot.com/en/docs/classic-ui/index.html): Linked from this page.
- [Modeling](https://docs.datarobot.com/en/docs/classic-ui/modeling/index.html): Linked from this page.
- [Model insights](https://docs.datarobot.com/en/docs/classic-ui/modeling/analyze-models/index.html): Linked from this page.
- [Evaluate](https://docs.datarobot.com/en/docs/classic-ui/modeling/analyze-models/evaluate/index.html): Linked from this page.
- [clustering](https://docs.datarobot.com/en/docs/classic-ui/modeling/time/ts-clustering.html): Linked from this page.
- [Series Insights](https://docs.datarobot.com/en/docs/classic-ui/modeling/analyze-models/evaluate/series-insights-multi.html): Linked from this page.

## Documentation content

# Series Insights (clustering)

The Series Insights tab for time series [clustering](https://docs.datarobot.com/en/docs/classic-ui/modeling/time/ts-clustering.html) provides series clustering information, including the cluster to which the series belongs, as well as series row and date information. Histograms, a non-clustering version of [Series Insights](https://docs.datarobot.com/en/docs/classic-ui/modeling/analyze-models/evaluate/series-insights-multi.html) for multiseries projects, are also available. The insight is helpful in identifying which cluster any given series was assigned to, and also provides an at-a-glance check that no single series is inappropriately dominant.

For multiseries, insights are reported in both charted and tabular format:

- The histogram for each cluster, which includes the number of series, the number of total rows, and the percentage of the dataset that belongs to that cluster.
- The table displays basic information for each series, such as row count, dates, and cluster membership.

Note that for large datasets, DataRobot computes scores and values after downsampling.

## Use Series Insights

On first opening, the Series Insight chart displays a list of the series, sorted alphanumerically by series ID.

Click Compute cluster scores to run histogram calculations and populate the table for the current model:

### Histogram

The histogram provides an at-a-glance indication of the make up of each cluster.

The following table describes the tools for working with the histogram:

|  | Element | Description |
| --- | --- | --- |
| (1) | Plot | Bins clusters by number of rows, percentage of total rows, or number of series in the cluster. To see all values, hover on a bin. |
| (2) | Sort by | Sets the sorting criteria for the bins. |
| (3) | Table filter | Filters the bins represented in the table below the histogram. |

Hovering on a bin displays the values for each of the plot criteria:

### Table view

The table below the histogram provides cluster-specific information for all series in the project dataset or, if filters are applied from the histogram, for series related to the selected clusters.

To work with the table:

- Use the search function to view metrics for any series.
- Use Options ( ) to set whether the series length information is reported as a time step or number of rows. Additionally, you can download the table data.
- Note that the start and end dates display the first and last timestamps of the series in the dataset.