Depending on your API version or the integration you’re using, our endpoints will either return an accuracy or a probability value in the response. The accuracy parameter returns how sure we are that this name is either male or female. The value is calculated by the number of records in our database. For example, if we have 100 samples of a name, 96 are female, and 4 are male, the accuracy is 96% (or a .96 probability). A low accuracy indicates that this name is probably used by multiple genders and cannot be conjugated to a specific gender.
While the name Andrea is male in Italy, Andrea is a female name in Germany and can even be both in the US. In this case, we provide an accuracy value in the query result, ranging between 0 and 100 (or a probability value between 0 and 1). It tells you how certain we are in having detected the correct gender. You can significantly increase the API’s result quality by providing some geographical information about your query. This can either be a country code, the browser’s locale, or an IP address.
We regularly update our data depending on the country and the available public data. Most western countries are updated once a year. Also, the distribution of names across genders may change over the years. For example, if a name was used exclusively by women in the 1970s, it may be used predominantly by male people decades later. That’s why we also use birth data for several countries, such as the US, to enrich the results. Our models try to take all these factors into account as well as possible. The returned accuracy value is regularly adjusted to reflect the actual usage in the population as accurate as possible. The value is supposed to provide a reasonable evaluation based on the last decades and may expresses a possible fluctuation. We do look at about the last 4 decades of the data. If you run a query and repeat the same query a year later, you may get a different result because our system might have dropped old data, and new data might have been added. Every time new data is added, we perform so-called integration tests afterward. In this process, our API is tested against a previously validated data set to ensure quality. This data set is continuously expanded with names and test cases to achieve the broadest coverage possible.
Languages and names are fluid and change over time. From customer to customer, data sets also vary a lot in quality, scope and origin. Therefore, we cannot guarantee that all results you receive from our API are 100% correct and match your data pool. But we can promise that we are always committed to providing you with the best results possible and that we regularly improve and update our algorithms. We also add new data on a very regular basis. You can find out more about our updates here. If you query a name, our endpoints will either return an accuracy or a probability value in the response, depending on your API version. The accuracy parameter returns how sure we are that this name is either male or female. The value is calculated by the number of records for this in our database. Since use cases differ significantly, we do not give any recommendations on the level of accuracy. Depending on your use case, it is up to you to decide what results and accuracy levels to accept. Even with an accuracy of at least 99%, there is a possibility that the result is incorrect. However, a value above 95% fits most use cases in general.
Our database contains 6,084,389 (2022) validated names from 58 different countries. All over the world we store 241,848 unique names. On an average we analyze about 10,000,000 datasets per month to improve the quality of our results.
Our email API can extract names from email addresses and provide the appropriate gender to this respective address. This can help you to personalize your emailings with a proper salutation. For example, from the email address "email@example.com", API will extract the name “Marie” and determine the correct gender, which is “female”. For details please take a look at our API Docs.
Both subscription types offer the same functionality. All API endpoints are available for both types and will return the same results. All subscriptions are limited to a different amount of requests per month.