> For the complete documentation index, see [llms.txt](https://docs.zingg.ai/zingg/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.zingg.ai/zingg/zingg-concepts/how-zingg-learns/zingg-models/similarity-model.md).

# Similarity Model

solving the accuracy problem

The similarity model evaluates each candidate pair that the blocking model passes through and produces a similarity score: a number between 0 and 1 reflecting how likely it is that the two records represent the same real-world entity.

It is a classifier, not a rules engine. For each pair, Zingg computes multiple features per field; character-level differences, string lengths, common transpositions, and prefix and suffix overlaps, and combines them into a single prediction. The threshold between match and no-match is automatically optimized. You do not set it manually.

The similarity model learns from your labeled pairs. Match labels show it what a true match looks like in your specific data. Non-match labels show it what different entities look like\
even when their field values are similar.

This is why label quality matters more than label quantity. A well-chosen set of 30 to 50 match pairs, covering the variation patterns in your schema, produces a more accurate model than\
a large set of casually labeled pairs.

{% hint style="success" icon="right-long" %}
For diagnosing similarity model behaviour and concept details → [Similarity Model](/zingg/zingg-concepts/how-zingg-learns/zingg-models/similarity-model.md)
{% endhint %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.zingg.ai/zingg/zingg-concepts/how-zingg-learns/zingg-models/similarity-model.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.