> ## Documentation Index
> Fetch the complete documentation index at: https://docs.topsort.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Optimizing Ad Selection and Ranking
export const LastUpdated = ({date, lang = "en"}) => {
const translations = {
en: "Last updated:",
es: "Última actualización:",
pt: "Última atualização:",
fr: "Dernière mise à jour:",
de: "Zuletzt aktualisiert:"
};
const label = translations[lang] || translations.en;
return <>
;
};
The components in this section are designed to work in real-time to help your
ad system select the most relevant candidates, enrich the auction with more
options, and rank the final results to maximize your business goals.
## Retrieval
Expands the pool of eligible ad candidates for any given auction. Instead of being limited to a narrow set of ads, the Retrieval API intelligently finds related and complementary products, boosting fill rates and increasing total ad revenue by creating more opportunities.
## Quality Score Prediction
Predicts the performance (e.g., estimated CTR and CVR) of ads before they are shown. This allows your ad server to prioritize ads that are not only high-bid but also highly relevant, improving overall campaign performance and marketplace revenue.
## Unified Ranking
Optimizes the final, blended order of both sponsored and organic items shown to a user. It moves beyond simple ranking by bid price and instead arranges items to maximize your primary business goal, whether that's net profit, overall conversion rate, or another custom metric.
***