The second iteration, of course, is to engage with every (valid, trusted, revenue generating, etc...) customer who searched, determine the quality of the results, and then feed _that_ information back into the algorithms. You could then bias based on domain experts (world class chef's feedback on BlueBerry Pies more important than an anonymous user)
It may be the case that (AllRecipes, TheFoodNetwork, Etc...) are NOT the best place to search for a recipe, and that, indeed, "http://pickyourown.org is knocking it out of the park this week.
There is a lot of room for search to improve - I think the company that beats google (if it's not google that does so first), will be the one that manages to start creating the search<-->Consumer<-->Search feedback quality looop.
Google may already collect enough data to do this. They track clicks on the search results, so they can see whether you liked the results, whether you went back to a different result after visiting your first, and whether you modify your search terms for another search because the first one did not work out.
It may be the case that (AllRecipes, TheFoodNetwork, Etc...) are NOT the best place to search for a recipe, and that, indeed, "http://pickyourown.org is knocking it out of the park this week.
There is a lot of room for search to improve - I think the company that beats google (if it's not google that does so first), will be the one that manages to start creating the search<-->Consumer<-->Search feedback quality looop.
PageRank was just the beginning.