The new feature comes six months after the startup acquired Discovereads, a book recommendation engine which is something CEO Otis Chandler cited as a sought-after feature among Goodreads users.

"With Goodreads, it's as if you combine your favorite librarian, your best friend, and a database of two million book titles into one person and ask 'what should I read next?'" said Chandler. "We're the Netflix of book recommendations. As members add more reviews and ratings, we keep improving our suggestions for them."

When most people hear "the Netflix of book recommendations" they tend to think of another Internet giant known for its powerful recommendation engine: Amazon. Goodreads says it can provide better book recommendations than Amazon can because it has more data about what people actually like and dislike, as opposed to just purchases, browsing history and ratings.

"For example, we have more than 174,000 ratings of the best-selling 'The Help' while Amazon only has around 4,400," said Chandler.

The site's book recommendations are heavily influenced by each user's book rating history, so people are encouraged to rate 20 books before checking out their suggested reading list. The service is now available in beta to all Goodreads users.

Two year old wine social network Snooth announced today that it is now powering wine recommendations for the 25,000 editor tested recipes on Conde Nast's food site Epicurious. Snooth says this is just the first of a number of big sites that its custom algorithm will power recommendations on. That cassoulet? Snooth suggests you serve a Montevina Terra d'Oro Syrah 2002 ($15) with it. Nice.

Wine with food has got to be one of the most familiar kinds of recommendations offline, but the online recommendation technology industry is a fast growing one. The belief is that quality recommendations will serve as searches you never knew you wanted to perform - helping users navigate from one logical option to another, possibly making more purchases as a result and hopefully being better served by the websites they visit.

A food site with good wine recommendations sounds pretty tasty to me. Snooth says its recommendations are based on ingredients, cuisine and cooking method.

Here's how it works. First, the keywords are parsed out of a recipe, then they are run through an extensive food dictionary and a long decision tree is then followed. Is it a soup, is it a salad, what is the primary taste? Beef and nuts tastes mostly like beef; beef and liver tastes mostly like liver. How the ingredients are to be prepared is determined by their proximity to preparation words in the recipe. Recipes with expensive ingredients will see more expensive wine recommendations, inexpensive ingredients (lobster vs. shrimp, for example) will yield less expensive wine suggestions. Goodbye old one-liners about "if you're eating chicken!"

Nibbledish, Cookstr, Chow? All cool recipe sites but no wine recommendations, much less very sophisticated ones. It's easy to see how recommendations can provide a competitive advantage in a niche like this.

How to Use it

InSuggest for bookmarks is very simple. You enter your Del.ico.us username, it looks at your archive of bookmarks and then recommends other similar pages you might like to bookmark. You can filter by one or multiple tags you've used. Up to 20 tag filter options are provided but you can enter any tag you've used in your account.

You can run anyone's Del.icio.us username through InSuggest and get recommendations, not just your own.

The interface is very nice, it's one of the best uses of Ma.gnolia's Thumbshot.org that I've seen yet, and the whole thing feels fairly smooth. In fact, it almost feels too smooth. The recommendations come to you very, very quickly. No where on the site, or in response to our email inquiry so far, can we find an explanation of how it works.

Despite that, it does seem to work well. There are a limited number of ways to parse Del.ico.us data, though, and we wouldn't be surprised if there's just a touch of caching going on. It's hard to say, but the end result is good. InSuggest developer Dennis Gustafsson was elected "Engineering Hero" by The Swedish Association of Graduate Engineers last year, according to search blog Pandia. So someone's seen behind Gustafsson's work and liked it.

Continued below.

Our Recommendations

Beyond some clarity around process and perhaps basic instructions on use, there are a few other things we'd like to see from InSuggest. The first is a feed for future recommendations. The display is in Javascript so we haven't been able to scrape it yet. We'd also love to see a Greasemonkey script for displaying InSuggest recommendations on top of the Del.icio.us bookmarking popup, archive page and item pages.

Other features that would be nice would be the option to input a Ma.gnolia username instead of just del.icio.us, tooltips to display full item titles that are too long for the basic display and the ability to exclude particular domains from future recommendations. Some sort of user feedback to inform recommendations should be doable.

Finally, the biggest fish in the pond when it comes to Del.icio.us recommendations is user recommendations, not just item level ones. We'd like to see other users be recommended, ideally with those who tend to find items of interest earliest privileged on the list.

That may be too much to ask for, though. It's hard to say. Feeds and user recommendations are the kinds of gifts that keep on giving, though, and are far more compelling than one-off recommendations.

For now, though, we think InSuggest for bookmarks is worth checking out. You could very well discover some things there that are just the kind of thing you've been looking for.

• SoundFlavor
• MusicIP
• Owl Multimedia
• Elbo.ws
• The Hype Machine
• SeeqPod Music
• Upto11
• 9ViBe
• Jamendo
• Goombah
• iLike
• Last.fm
• ChartU
• Mog
• MyStrands
• Qloud
• U.[lik]
• herkesdinlesin

If you've used any of the above services, let us know in the comments. I'd like to check out a few of these and see how their recommendations stack up.

As is typical for Apple, the company is not exactly transparent when it comes to describing how the 'Genius' feature actually works. It looks as if Apple compares your music selection to that of other users and then builds its recommendations based on this. We assume that iTunes looks at data about play and skip counts, beats per minute (which is available for all songs in the iTunes store), ratings, and playlists.

Because these recommendations are at least partly based on the libraries of other iTunes users, iTunes periodically downloads updated recommendations. You can also force an update from the 'Store' menu.

One fact that surprised us was that Apple often returned playlists for songs that were clearly mislabeled, which has led us to speculate if Apple, during the first run of Genius, actually creates an acoustic fingerprint for every song.

According to Apple, all the uploaded information is anonymized.

Does it Work?

In our tests, the recommendations and playlists were often spot-on, but also a bit inconsistent. Sometimes we would get great recommendations based on songs from rather obscure bands, while we sometimes couldn't get any recommendations based on songs from more popular and contemporary artists. For classical music, the recommendation feature basically didn't work at all.

We also noticed that the recommendations tend to favor more popular mainstream artists, but that could easily be a function of the current user base.

Apple points out that the recommendation engine will get better over time, as more users start uploading their information. It would be nice, however, if Apple also gave users a chance to tweak settings for themselves or at least gave us more information about how these recommendations are calculated.

One minor annoyance when using the recommendations is that if you decide to build a Genius playlist based on a song that is already playing, iTunes starts the song over after creating the new playlist.

What about Last.fm and Pandora?

As Last.fm co-founder Marting Stiksel pointed out in an interview with Wired's Eliot Van Buskirk, the 'Genius' feature basically validates what other music recommendation services have been doing for a long time.

It's also important to point out that a lot of other music recommendation services have strong, built-in social networking functions. Apple, even though it now has information about the listening habits of a large chunk of its users, does nothing to connect these users. One neat function, for example, would be for iTunes to show playlists from other users that have a certain songs in it. For now, though, it doesn't seem as if Apple is interested in adding these social aspects to iTunes anytime soon.

Rediscovering Music

For now, when it works, Apple's recommendations are actually a very nice way of rediscovering a lot of music that had long been sitting in our jukebox but never saw the day of light. We also assume that the shopping recommendations in the sidebar will drive more traffic to Apple's music store, especially once the recommendations get a bit better and users get comfortable with trusting Apple's recommendations.

Your recommendations will be visible when you use Google's Place Search and will also appear on Maps.

While the Google versus Facebook battle seems to be getting a lot of attention, Hotpot may well have more effect against Yelp, the site long associated with local reviews and recommendations. Google has over 50 million places already, linked to maps and reviews (many of them Yelp reviews).

By moving the recommendation and review process "in house," so to speak, by being able to provide an algorithm to recommend sites based on preferences, not merely location, and most importantly perhaps, by integrating these recommendations with mobile, Maps and Search, Google's Hotpot may be a "killer" location-based app. Sorry, Yelp.

The highlight of the new version is recommendations. The new Diigo offers a number of social networking type features that in-and-of themselves aren't worth a lot to me, but if they can do some number crunching and recommend people and content that I may want to subscribe to - that's gold.

What's the biggest crime committed by Del.icio.us? It's not leveraging the huge amount of data the service holds for some recommendations. Why on earth, in this data-centric era, isn't every social bookmarking service making bookmarking social and smart? If Yahoo! held an Amazon-style contest for recommendation algorithms that could be run against Del.icio.us, they could set up a Yahoo! News style page that was personalized like nobody's business. We'd all come back daily to read Del.icio.us, they could run ads up the wazoo and everyone would be beside themselves with happiness.

Instead we'll have to look to a pre-acquisition startup with neither network effect nor scaling problems. Diigo has potential to change the social bookmarking game just because they are offering recommendations. The recommendations aren't even very good yet because there's very few people using the service and the algorithm appears quite simple. I imported several hundred bookmarks from Ma.gnolia and perhaps Diigo will think deeper thoughts about my history after a few hours. I'm not so sure, though. It's still worth a look because it has so much potential.

You might also like the annotation features, though in all likelihood they will prove more trouble than they are worth unless you're an academic. You can associate an OpenID account with your Diigo account now, too. That's good.

Trust

Checking out Diigo could be pretty pain-free. The service does a good job of importing your bookmarks from elsewhere and allows you to publish simultaneously to your account at Del.ico.us, Ma.gnolia or Simpy. If, that is, you are willing to trust the Diigo people with the password to your usual social bookmarking account. Doesn't Ma.gnolia at least have oAuth support so I don't have to do that? Discussion about user authentication protocols as part of data portability seem common enough by now that it's outright offensive to be asked for your password to another web app. If you can deal with that, then there's no reason not to give Diigo a try.

Check out Diigo for yourself, it could be just what you're looking for. It's getting closer to something I can imagine using regularly and really appreciating - but it's not there yet. I'll keep an eye on the recommendations feature because if that ends up working out well, it would be reason enough to switch to Diigo.

Recommendations

In a tweet, the Noovo team told us that the app uses "state-of-the art deep graph mining and text extraction to recommend relevant content to users." A recent blog post explained further that Noovo uses "advanced algorithms to filter out the noise for you and recommends you the most relevant stories based on who your influencers are".

Further, Noovo recently deployed integration with dbpedia, the structured data version of Wikipedia. Noovo stated in its blog that this enables item-based recommendations, in other words pulling out topics from your user behaviour and that of your social network.

In many ways the recommendations part is like Digg's feature of the same name, in that it recommends interesting content from the site's community that you may like. And the more you use Noovo, the better the recommendations supposedly become.

Features Galore

Noovo is an interesting app and it sports a visually appealing interface. However, some of the main features are hard to find and then understand when first getting started. For example we had to hunt around to find out where the recommendations are (on the oddly named 'Cover' page, as it happens), and the hour glass icon is confusing at first glance (when you click it, it shows how the recommendations came about).

Adding content can also be cumbersome, unlike Tumblr where it is very simple and intuitive.

It's fair to say that these issues arise because Noovo has so many features - one could argue too many. But that also may end up its strength, because if you're looking for a central place to aggregate, share and discover cool content on the Web - Noovo could be a great choice for you. The community is small right now, but there is no shortage of colorful content to browse. Check out Noovo CTO Matej Pangerc's page, for example - you can see straight away that Noovo is very akin to Tumblr, Soup.io (my personal favorite) and other lifestreaming blog platforms.

We'll be keeping an eye on Noovo and testing it out some more. Let us know your thoughts in the comments.

Crowley's talk was first reported by watchdog blog About Foursquare, where a video of the 20 minute presentation from Picnic can be found.

"Users would be awarded experience points as a sushi expert or skiing expert based on their checkins in those categories, for example," About Foursquare writes. "Their recommendations could carry more weight and be used to suggest places other users should visit."

Data about real-world behavior, combined with social connections, geographic locations, annotations of locations via tips and to-do items - that's a potent mix for possible innovations in any number of features for this service, or services built on top of it.

Recommendations: High Risk, High Reward

Recommendation is low-hanging fruit, but whereas recommendation of online content from other services is relatively low-impact, recommendations that a person set foot in a particular venue probably carries a lot more weight. For better and for worse. If Foursquare recommendations are unsuccessful or feel counter-intuitive to users, users may be very unhappy about that.

No doubt the company is testing the feature thoroughly among its New York City staff, but whether recommendations can succeed outside a venue-dense city with intense support for an otherwise small social network remains to be seen.

Foursquare claims to have approximately 3 million users, neither the biggest (that's Facebook) nor the smallest player in the location based social networking market. It may be the most consistently innovative competitor in this space, though.

In addition to recommendations, the company has long talked about incentivization of real-world behavior. Today, for example, Foursquare announced a partnership with CNN, which will give a "healthy eater" badge to anyone who checks-in at one of ten thousand farmers markets. It's unclear whether a dorky apple badge with CNN emblazoned on it is going to incentivize anyone to do anything - but it's a start and an interesting idea.

Imagine checking in at a farmer's market, then later receiving recommendations to restaurants that cook with locally-sourced food when you check-in nearby. It's got to be just a matter of time before big companies like McDonald's start incentivizing fun and Happy Meals lest we all get too many farmers market recommendations.

That might sound simple, but it's important and, if the recommendations prove good, there's probably some complicated math going on behind the scenes to determine what you're like. Google leadership has said for months that its future lies not in serving up results in response to your search queries, but in telling you what you want to do before you even ask. There's something about this news that brings that promise to mind for me.

The Age of the Algorithm

Some people argue, in fact, that this kind of taste detection and recommendation technology is part of a larger trend that will become a key part of the technology industry of the near-term future.

Dr. András Faragó, Computer Science Professor at the University of Dallas, said in an interview last week that we're entering the Age of the Algorithm.

"While no one questions the value of software today, the underlying intellectual content, the algorithms, are still viewed by many as something without hard value. The value is still typically assigned to the implementation, not the algorithm. In a sense, algorithms up until very recently have had the same relationship to software implementation as software previously had to hardware: icing on the cake.

"On the other hand, there are more and more situations, as signified by the Heritage Provider Network's $3 million prize (for early detection of people at high risk of later hospitalization), where the really hard part is finding the right algorithm. Once it is found, the implementation can be done by any skilled team, and I believe this may show the emergence of a trend in which in which the industry starts recognizing the real, hard value of sophisticated algorithms."

In many cases, that hard-fought battle will end up looking to end users like low-key, smart recommendations of new restaurants in new cities.

We asked and you answered and we culled your responses from the original post on ReadWriteWeb, Twitter and Facebook and used Storify to present it all back to you. If you have additional responses, please leave them in the comments.

CleverSet, now known as 'ATG Recommendations', is described on ATG's website as "a predictive recommendations service". It's just one part of a suite of e-commerce "optimization services". The company claims that it is differentiated from other recommendations services by its focus on commerce and the fact that it is a stable, profitable company. In the 2008 year the company did $164M revenue "with profitability". That figure includes many services and licensing revenues, of which product recommedations is just one. ATG was founded in 1991 and it did an IPO in 1999, so it does appear to be more experienced than competitors like richrelevance.

Predictive Recommendations

ATG's core product is an e-commerce suite, which it says is used to power hundreds of online store fronts. Its "e-Commerce Optimization Services", which includes recommendations, can be used on other e-commerce sites as well as those powered by ATG. The company told us that their products aim to increase the following 3 things: conversion rates; order value; and customer attention.

ATG calls its approach to recommendations a "blended approach", which aims to predict what the consumer wants to buy next. The recommendations come from a combination of user, site and product data. Elements include purchase history, the time of day, where the user clicked from, what browser they use, product catalog variables, historical shopping information, click-stream data, and more. Out of all this ATG provides what it calls "predictive recommendations".

How is ATG Different From richrelevance?

ATG's approach sounded very similar to that of richrelevance. So we asked ATG: what's different? Bruce D'Ambrosio, founder of CleverSet and ATG's Chief Scientist, responded that richrelevance is similar, but that it is "mostly a subset" of what ATG Recommendations does. He said that ATG is focused on bringing the merchandiser "into the conversation with the visitor", whereas richrelevance perhaps has less focus on merchandiser and more on the user.

D'Ambrosio further said that ATG models the visitor in both current and longer term sessions. The method it uses is called "Statistical Relational Learning" (SRL), whereby ATG integrates information about the actual user with "similar visitors". It also incorporates relational data about the product and "context of use".

Another key piece of data that ATG focuses on is "engagement", by which it means what fraction of users/buyers interact with recommendations. D'Ambrosio said that they see an enormous amount of this engagement activity before users buy products.

The Netflix Prize

As an interesting aside, we asked D'Ambrosio, as a very learned and experienced engineer in this field, what his thoughts were on the Netflix Prize. We mentioned the Napoleon Dynamite problem, whereby products like that are hard to recommend against.

D'Ambrosio replied that to win the Netflix Prize will require a re-definition of the problem, by "dramatically expanding the scope of the information". He said that most of the interesting information required to do Netflix recommendations well is actually off-site - e.g. product data that's not in the catalog on Netflix. He thinks that to win the Netflix Prize, contestants must gather more information about products like Napoleon Dynamite.

Conclusion: Big Player

As well as finding that it's a crowded market, another thing we've discovered in this series is that comparing recommendation engines directly to one another is nearly impossible. Firstly because each customer has different needs and so unless the customer has tried more than one product, they won't be able to accurately compare them. But secondly, each recommendation engine has a different approach and their algorithms are complicated - and well protected. Who knows what is really under the hood of Baynote, richrelevance or ATG.

However, ATG does have a good track record behind it; and we were particularly impressed by the knowledge of Bruce D'Ambrosio - surely one of the company's best assets in recommendations technologies. So if you're an e-commerce shop looking to implement recommendations, ATG seems like a relatively safe bet.

Zemanta is a startup that captures more internet buzz words than almost any other I can think of:  semantic web, rich media, recommendations and real-time.  I mean that in a good way, too.  In addition to a browser plug-in and this new relationship, Zemanta is available through partnerships with blog platforms Movable Type, Blogger.com and Scribefire. The company claims it now reaches 30% of the blogs online.

Appazaar learns which applications you find interesting by tracking your application usage and comparing you to other people with similar interests, much like Apple's Genius does in the App Store. It also takes your real-time location into account.

Like other app discovery tools, appazaar makes recommendations based on users' interests and the apps they've previously downloaded. But it also uses context - time and location - to serve up suggested apps. "A use that has never been in a specific context before receives recommendations on what other users have used in a similar context before," the researchers wrote in a paper that will be presented at an upcoming international conference on recommendation engines in Barcelona. In downtown Portland? Try the PDX Food Cart Finder.

Appazaar is available on the Android Market, but it's still new, so don't judge it too harshly. The more people start using it, the better its recommendations will get.

Despite its name, Lunch.com isn't just a website for dining recommendations. Instead, the name derives from the idea that the kind of conversations you would have with a friend over lunch can be corralled into a Web application for the purpose of personal recommendations.

Lunch has always eschewed the typical "re-friend all your online friends" method of connecting you with others in favor of connecting you with those who are most similar to you. It does this by way of its key feature: the Lunch "Similarity Network."

Until now, the service had to sort of trick you into sharing your recommendations and interests with the community by way of online games. As with Amazon's "improve your recommendations" feature, the games on Lunch - today there are over 300 - let you rate items like movies, books, food, sports, music, cars, fashion, politics, gadgets... anything, really. The idea is that rating items in a game-style interface makes the process of sharing your interests fun.

However, these games aren't there just so you can have fun - without knowing your interests, Lunch.com simply cannot function. It wouldn't know you or what you like and therefore couldn't make recommendations or connect you with others.

Forget Games, Import Likes for Instant Personalization

But, let's face it, however "fun" the games are, playing them still takes effort. Wouldn't it be great if the site already knew what you liked? Well, now it will.

With the upcoming Facebook "like import" feature, you'll be able to instantly personalize Lunch and then be able to enjoy its recommendations without spending any time training its algorithms to know you better.

This, of course, is dependent on whether or not you've been active on Facebook, but with 500 million users worldwide using the social network, it's a good bet that most of us are.

There has been a large focus in the tech community on the more negative aspects of Facebook's changes due to the social network's user privacy violations and questionable level of openness, but the Open Graph API the company implemented for developers (detailed here) is one of its better new features. With this API, after a user grants permission, Web developers can access Facebook profile information - like profile details, friend lists and, as Lunch shows, Facebook likes - and import it into their own Web service or application. The benefits and drawbacks to this trade-off - privacy for personalization - are left for users to consider and decide upon. Lunch.com is betting that most users will opt-in... and we bet that most will, too.