# Search Query Suggestion on Online A/B Test Real-world traffic

Source: [Search Query Suggestion on Online A/B Test Real-world traffic](<https://www.sota2.com/research/sota/search-query-suggestion-on-online-a-b-test-real-world-traffic>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-06T08:21:04.641Z

Evaluation of a Search Query Suggestion model based on live A/B test results from real-world traffic, focusing on metrics related to result diversity, item exposure, and click-through rates.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Search Query Suggestion |
| Dataset (including any stated split) | Online A/B Test Real-world traffic |
| Metric | Few/No-Result Rate |
| Unit | PERCENT |
| Direction | Lower is better |
| Results loaded | 1 of 1 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Few/No-Result Rate](<https://www.sota2.com/research/sota/search-query-suggestion-on-online-a-b-test-real-world-traffic.md?metric=Few%2FNo-Result%20Rate>): Lower is better; unit: PERCENT.

- [Unique Item Exposure](<https://www.sota2.com/research/sota/search-query-suggestion-on-online-a-b-test-real-world-traffic.md?metric=Unique%20Item%20Exposure>): Higher is better; unit: PERCENT.

- [Average Item Exposure](<https://www.sota2.com/research/sota/search-query-suggestion-on-online-a-b-test-real-world-traffic.md?metric=Average%20Item%20Exposure>): Higher is better; unit: PERCENT.

- [Category Diversity](<https://www.sota2.com/research/sota/search-query-suggestion-on-online-a-b-test-real-world-traffic.md?metric=Category%20Diversity>): Higher is better; unit: PERCENT.

- [Session CTR](<https://www.sota2.com/research/sota/search-query-suggestion-on-online-a-b-test-real-world-traffic.md?metric=Session%20CTR>): Higher is better; unit: PERCENT.

- [PV CTR](<https://www.sota2.com/research/sota/search-query-suggestion-on-online-a-b-test-real-world-traffic.md?metric=PV%20CTR>): Higher is better; unit: PERCENT.

- [Average SUG Input Length](<https://www.sota2.com/research/sota/search-query-suggestion-on-online-a-b-test-real-world-traffic.md?metric=Average%20SUG%20Input%20Length>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Few/No-Result Rate | Result date | Report paper |
| --- | --- | --- | --- |
| LocalSUG | 2.56 | Not recorded | 69aa5f702d603e6de3e4180e |

### LocalSUG

Few/No-Result Rate: 2.56. Result ID: 69aa8e6d6dbb7075b95440e2.

[Reporting paper](<https://www.sota2.com/research/paper/69aa5f702d603e6de3e4180e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69aa5f702d603e6de3e4180e.md>)

Recorded evaluation configuration: {"Traffic Coverage":"10%","Duration":"one week"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.