> ## Documentation Index
> Fetch the complete documentation index at: https://docs.thedatacity.com/llms.txt
> Use this file to discover all available pages before exploring further.
# How are 'Similar Companies' identified?
> You can find the most similar companies in the 'Full Info' of a selected company in either EXPLORE or ANALYSE. What does this mean, and how should it be used?
We offer two methods for finding similar companies: **Semantic Similarity** and **Composite Similarity**.
**Semantic Similarity** leverages cutting-edge LLM-based methods to identifying similarity between companies based on the text on their websites.
More detail can be found [here](https://thedatacity.com/blog/building-the-industry-engine-similarity-score-update/).
**Composite Similarity** combines the approach of the **Semantic Similarity** with a measure of similarity also based on structured business characteristics, such as sector, location, and employee count.
**Quick Guide**
* **Semantic** - broader exploration, more cross-sector matches. Useful for finding companies when building a Smart List, etc.
* **Composite** - sector-aware recommendations, structural alignment. Useful when you need matches that share fundamental business attributes, i.e. when company size and location are important filters or signals, or you're looking for true industry peers or competitors.
Try both and compare if you're unsure. Both return results in the same format.
**Please note**: This methodology is not the same as our classification engine, which we use to build our RTICs. It does not generate a comprehensive list of a sector, instead it only identifies the companies which are most similar to the given company