Tuesday, March 07, 2006


While preparing my posting about Personalized Search I stumbled upon Findory as one of the heralds of the new Personalized Search era. The bottom line is that Findory tries to save users' time by giving them more relevant results, but most of the time each result contains relevant information mixed with irrelevant information and the users are still wasting their time. So what's the big deal?

Other than that on most popular search engines a query about QTSaver brings some results – on Findory none. What did I do? I submitted my Blog to Findory`. I got a message saying that "It might take a few happy seconds. Patience is a virtue". Then I waited and waited but nothing happened. Let's hope that in a few days I'll search for my postings and find them on Findory

Here are some relevant excerpts I collected after entering one query about Findory to QTSaver:



September 3, 2005 Company: Findory Launched: January 2004 Location: Seattle, WA

Findory, which is almost two years old, is a pioneer in this area and has a unique solution. Findory is a personalized newspaper that evolves, quickly, as you click and read. Greg and his co-founder Alex Edelman, spent years at Amazon prior to creating Findory, and gathered extensive experience in recommending new products to Amazon users. They have three silos of information, all personalized - news, blogs and search. Findory looks at your historical clickstream and presents only related information. It evolves real-time as you search, browse, click and read stuff that interests you



Findory is a personalized news site, started by Greg Linden that aggregates thousands of news sources. It learns from the articles users click on to build a personalized news page for each user.  Findory appears to use a collaborative filtering algorithm to recommend interesting news items. A notable feature of Findory is that it does not require users to register or to explicitly rate items. Instead, it uses an anonymous cookie and personalizes using your reading history.



Findory is a personalized news and weblog reader. It learns from the articles you read, searches thousands of sources, and helps you discover news you would otherwise miss.



Top Stories from My Favorites is a personalized selection of articles picked from your favorite feeds. It's designed to emphasize interesting articles based on your reading habits rather than forcing you to read every single post from every single blog in your feed reader.  Findory Favorites now allows you to read up to 200 stories, 20 at a time. I added a feature called Findory Tags that automatically extracts common keywords used by a news source or weblog.



Our API enables developers to retrieve Findory news and blog article data by making parameterized URL requests over HTTP (otherwise known as REST). The results are returned in RSS format for your convenience



Findory has built up a loyal following in the nearly two years since its launch. However, many users requested the ability to include RSS feeds of their choice directly into their blog and news channels. Greg and Alex just added this functionality, making Findory nearly perfect as a news source and reader.

Findory users now have the ability to add feeds directly into Findory - one at a time, via an OPML cut-and-paste or simply by directly importing your feeds from Bloglines, if that is your current reader.

Once you’ve imported these feeds, the powerful Findory personalization engine takes over and presents posts to you in a personalized way, based on what you (and community members like you) tend to find interesting.

Findory is squarely attacking the current efforts by Attensa, SearchFox, Personal Bee and others to present your feed information in a more intelligent and useful way. The standard readers quite simply don’t work for power users with 100+ feeds any more - and companies are trying very hard to find ways of sorting through this information for you before you start to read. And unlike Attensa (who hasn’t launched their personalization product yet) and SearchFox (in private beta, although you can get an invite fairly easily), Findory is live and open to everyone.



Greg Linden is founder of Findory, and author of the popular blog "Geeking with Greg". Findory is a personalization and recommendation service that helps users find news stories and blog posts of interest to you. Findory also has a search engine built in that personalizes its results based on your past searches and clicks. Think Memeorandum combined with Google personalized search, powered by a collaborative filtering engine.

Findory is primarily a recommendation engine.

 Personalization learns what you want from what you do. Using personalization, Findory helps focus your attention and surface things that you may not have been able to find on your own.

 Findory is quite a bit different. Unlike Digg or Jookster, there is no explicit voting or listing friends. Findory's personalization learns from what you do, finds other people with similar interests to yours, and shares what they have found, all implicitly, all anonymously, all without any effort. Unlike Memeorandum, Wink, and Digg, every reader sees a different page on Findory, each page personalized to each person's interests.

When you read articles on Findory, Findory looks for other readers who might have the same interests as you, and then shares the articles they found. It is a little like social networking sites where you explicitly list all your friends, then explicitly share things you found among your friends. But, with Findory, friends are found for you automatically and anonymously. With Findory, the sharing is done quietly and implicitly, all with no effort.Just read articles, that's it. Findory does all the work for you.

 The personalization techniques used by Findory fall loosely into the class of collaborative filtering algorithms. However, naive collaborative filtering has well known quality, performance, and scaling problems. Findory creates fully personalized pages in real-time, works even if someone has read only a few articles, learns immediately from new data, and can scale to millions of users.

 To my knowledge, there are no other start-ups doing personalized information like Findory. However, the search giants have made tentative efforts toward personalization. Google has an experiment with "recommended stories" on a small section of the Google News page and also has an active effort in personalized web search.

Powered By Qumana

1 comment:

Chris Fairbanks said...

One of the big problems Findory has with getting new feeds into the system is that they have a manual approval process for each new feed, and they get so much spam (porn feeds, ad feeds, etc) pushed into their forms that the real sites get lost in the mix. It took me a few weeks and an eventual email conversation to get Williamsburger included in their blog ratings system.

I agree, it does seem like Findory should be doing a better job than it is at giving only relevant results. Their search capabilities are frequently pretty lacking as well.

In my experience, though, as someone with about 800 articles read through Findory at this point, the relevant ones (marked with the Findory icon) are frequently well-tailored to my interests.