I have begun Research on the I.R. Reverse Engineering Project, which will attempt to identify the technologies and methodologies employed by major Search Engines in regards to the way that search results are retrieved and organized. This project is a continuation of previous research which I conducted that addressed PageRank and other Google technologies.
A white paper which I have written summarizes the results of that research and is available in our White Papers section.
The primary elements of research will be identification and study of patents (including patent applications) and a comprehensive study of Search Engine Results Pages, for both specific and random search terms. Finally I hope to conclude the project by creating small scale working models which can reasonably simulate the ranking and document retrieval techniques of the Search Engines studied.