# \#quality **URL:** https://forum.datacebo.com/tag/quality/5.md [Latest](https://forum.datacebo.com/latest.md) · [Categories](https://forum.datacebo.com/categories.md) · [Tags](https://forum.datacebo.com/tags.md) --- ## [Provide your segments to the SegmentSynthesizer](https://forum.datacebo.com/t/provide-your-segments-to-the-segmentsynthesizer/412)
**Author:** [@neha](https://forum.datacebo.com/u/neha)\ **Replies:** 0\ **Last updated:** [February 26, 2026, 9:34pm UTC](https://forum.datacebo.com/t/provide-your-segments-to-the-segmentsynthesizer/412 "2026-02-26T21:34:14Z")
Our SegmentSynthesizer is a specialty synthesizer designed to model highly segmented data with higher accuracy. If your data table has high segmentation, it contains groups that behave in different ways. We’ve recently u… --- ## [The importance of leading zeros](https://forum.datacebo.com/t/the-importance-of-leading-zeros/408)
**Author:** [@neha](https://forum.datacebo.com/u/neha)\ **Replies:** 0\ **Last updated:** [February 11, 2026, 2:21pm UTC](https://forum.datacebo.com/t/the-importance-of-leading-zeros/408 "2026-02-11T14:21:07Z")
We’ve recently made an important enhancement to the way SDV imports data: We now retain leading zeros from the original CSV file when loading it into Python, which can dramatically improve your usage of SDV. Leading zer… --- ## [Measuring significant correlations](https://forum.datacebo.com/t/measuring-significant-correlations/403)
**Author:** [@neha](https://forum.datacebo.com/u/neha)\ **Replies:** 0\ **Last updated:** [February 4, 2026, 3:51pm UTC](https://forum.datacebo.com/t/measuring-significant-correlations/403 "2026-02-04T15:51:11Z")
In our most recent release, we made an important change to the way we measure synthetic data quality. From now on, the Quality Report will evaluate whether the synthetic data matches strong correlations from the real dat… --- ## [Distributions of features in synthetic data](https://forum.datacebo.com/t/distributions-of-features-in-synthetic-data/207)
**Author:** [@yuntien.lee](https://forum.datacebo.com/u/yuntien.lee)\ **Replies:** 16\ **Last updated:** [February 4, 2025, 6:27pm UTC](https://forum.datacebo.com/t/distributions-of-features-in-synthetic-data/207 "2025-02-04T18:27:24Z")
Hi Datacebo team, After generating synthetic data based on the metadata, inspecting using synthesizer.get\_learned\_distributions, all columns show ‘truncnorm’ distribution, but we used whatever the default settings were,… --- ## [SDV HSA Synthesizer not preserving correlations of orginal data](https://forum.datacebo.com/t/sdv-hsa-synthesizer-not-preserving-correlations-of-orginal-data/279)
**Author:** [@joachim.zaspel](https://forum.datacebo.com/u/joachim.zaspel)\ **Replies:** 3\ **Last updated:** [January 20, 2025, 8:35am UTC](https://forum.datacebo.com/t/sdv-hsa-synthesizer-not-preserving-correlations-of-orginal-data/279 "2025-01-20T08:35:12Z")
Background I created a very simple data model and generated test data using a python script to evaluate if SDV (HSA Synthesizer) is able to generate synthetic data that preserves correlations or data patterns found in t… --- ## [Maintaining Cardinality Between Tables](https://forum.datacebo.com/t/maintaining-cardinality-between-tables/246)
**Author:** [@giovanni.circo](https://forum.datacebo.com/u/giovanni.circo)\ **Replies:** 3\ **Last updated:** [August 27, 2024, 9:13pm UTC](https://forum.datacebo.com/t/maintaining-cardinality-between-tables/246 "2024-08-27T21:13:39Z")
We have a database of claims, procedures, and diagnoses, along with a header table. The header table uniquely defines records by MBR\_ID, CLM\_ID, and CLM\_HASH\_KEY. The expected output is that every claim in the clm\_detail… --- ## [Quality Report Timing](https://forum.datacebo.com/t/quality-report-timing/208)
**Author:** [@pranav.rupireddy](https://forum.datacebo.com/u/pranav.rupireddy)\ **Replies:** 4\ **Last updated:** [June 11, 2024, 9:47pm UTC](https://forum.datacebo.com/t/quality-report-timing/208 "2024-06-11T21:47:48Z")
I am noticing that the quality report takes a very long time (upwards of multiple days) - I was wondering if you had any suggestions to speed this up or if this could be improved? --- ## [Duplicated values within a group](https://forum.datacebo.com/t/duplicated-values-within-a-group/198)
**Author:** [@yuntien.lee](https://forum.datacebo.com/u/yuntien.lee)\ **Replies:** 3\ **Last updated:** [June 6, 2024, 6:18pm UTC](https://forum.datacebo.com/t/duplicated-values-within-a-group/198 "2024-06-06T18:18:24Z")
metadata.xlsx (18.1 KB) Hi Datacebo Team, After finishing a run with the metadata attached we have noticed that the YearMo in the synthetic mem\_yearmo table has some duplicated values for a certain MemberID. YearMo val… --- ## [\[Resolved\] Synthetic Data with Standardized Predictor Variables (Constant values)](https://forum.datacebo.com/t/resolved-synthetic-data-with-standardized-predictor-variables-constant-values/182)
**Author:** [@lpalayangoda](https://forum.datacebo.com/u/lpalayangoda)\ **Replies:** 7\ **Last updated:** [May 13, 2024, 9:58pm UTC](https://forum.datacebo.com/t/resolved-synthetic-data-with-standardized-predictor-variables-constant-values/182 "2024-05-13T21:58:59Z")
@kalyan : I am working on a simulation to find the performance of the synthetic data generation process for the DOE. The original predictor variables are either -1, 0, or 1 (low, mid-point, and high); however, when I sy…