[[["易于理解","easyToUnderstand","thumb-up"],["解决了我的问题","solvedMyProblem","thumb-up"],["其他","otherUp","thumb-up"]],[["很难理解","hardToUnderstand","thumb-down"],["信息或示例代码不正确","incorrectInformationOrSampleCode","thumb-down"],["没有我需要的信息/示例","missingTheInformationSamplesINeed","thumb-down"],["翻译问题","translationIssue","thumb-down"],["其他","otherDown","thumb-down"]],["最后更新时间 (UTC):2025-08-18。"],[],[],null,["# Measure performance\n\nThe Search for commerce console provides metrics to help you\ndetermine how incorporating Vertex AI Search for commerce is affecting your\nbusiness.\n\nView metrics\n------------\n\nYou can view summary metrics for your project on the [**Analytics**](https://console.cloud.google.com/ai/retail/catalogs/default_catalog/analytics/) page. This page displays\nsite-wide metrics about revenue and orders. See [Summary\nmetrics](#summary-metrics) for metrics definitions.\n\nFor metrics specific to your serving configs, go to the\n[**Serving Configs**](https://console.cloud.google.com/ai/retail/catalogs/default_catalog/configs/) page.\nClick a serving config name and select the **Analytics** tab to see its\nmetrics. See [Configuration-specific metrics](#config-metrics) for metrics\ndefinitions.\n\nMetrics definitions\n-------------------\n\nThis table provides definitions of the summary metrics that\nVertex AI Search for commerce displays on the **Analytics** page.\n\n### Configuration-specific metrics\n\nYou can see metrics for a specific serving config on the\n[**Serving Configs**](https://console.cloud.google.com/ai/retail/catalogs/default_catalog/configs/) page.\nFor metric graphs, click the configuration name and select the **Analytics**\ntab.\n\nThis table provides definitions for configuration-specific metrics.\n\nTo track clicks from a serving config, Vertex AI Search for commerce\naligns the recommendations in `predict` responses and search results in `search`\nresponses with ingested user events. If a clicked item appears in the `predict`\nor `search` responses for the same visitor ID within a one hour time window, the\nclick and purchase is treated as a result of the recommendation or search result.\n\nWhen you configure your recommendations or search requests for the first time, you\nshould confirm that:\n\n- Visitor IDs in the request are the same as the visitor IDs you used in event ingestions.\n- The timestamp in the response roughly matches the timestamp for that event.\n\nWhen Vertex AI Search for commerce metrics are compared to the ideal expected result,\nor ground truth, the values might be lower, but the trends align.\n\nUnlike for recommendations, the process of attributing click to search requests is not fully automatic. So for metrics to work for Vertex AI Search for commerce, an [attribution token](/retail/docs/attribution-tokens) is required. However, attribution tokens are not needed for recommendations user events."]]