![Alamy Images [home]](/images/alamy.png)
AlamySearch
Alamy released its new search system, AlamySearch on 10th October 2006 and since then a number of improvements have been made. The system is constantly evolving.
The latest system consists of three main components, giving a combined score, to determine image positioning; namely AlamyRank, the Search Engine and the Diversity Algorithm.
AlamyRank
AlamyRank assigns a score to a collection based on the number of times images from a pseudonym have been clicked or purchased in proportion to the number of times they have been viewed by customers.
AlamyRank produces a rank per collection of images (per pseudonym) rather than per image. So a contributor with more than one pseudonym will have been assigned more than one AlamyRank. Ranks are re-calculated roughly every 100 days using the previous 300 days data. New images added to an existing pseudonym inherit the rank for this pseudonym. New pseudonyms are assigned the median rank. This should give them enough visibility from which to calculate a true AlamyRank in time.
The Search Engine
The search engine finds images that match the terms entered by the customer. Currently, these words may be in any of the caption, keyword, location fields, or in the pseudonym/agency name. Each field is weighted differently, please see the advanced details for more information. The current search engine was developed in house from the ground up, which allows us full control of how the system behaves, particularly in terms of relevancy.
The Diversity Algorithm
The Diversity Algorithm comes into play once AlamyRank and the search engine have established which images have the highest score. Its purpose is to ensure that the images returned are inter-dispersed among images of similar rank. This means that search results are not dominated by the collections with the highest combined score and that no one contributor dominates the results. The strength of the Diversity Algorithm diminishes if the gap between the collection rankings is significant. This means that clusters of images from a single collection can appear close together in the search results if there are no competing images available of a similar AlamyRank and/or relevancy score.
Improving your rank
To ensure that customers and contributors benefit fully from the new system, feedback tools are provided to contributors to help them improve the rank of collections. The tools, called AlamyMeasures, report customer activity and suggest modifications to submissions and metadata. The goal is to allow contributors to make informed decisions about how to submit and describe their pictures, as well as getting an insight into what buyers are searching for.