June 28, 2011
Recommendation Engines: 5 Lessons from Pandora, StumbleUpon and YouTube

I went to SXSW this year but happened to miss a really cool panel on Recommendation Engines. Luckily, it was recorded here. I figure that most of you have companies that allow for an endless number of combinations, so I think that some of the lessons from this panel might be interesting to you, too.

What I had in mind when I took notes from the recording is that MyCereal.com, before it shut down, didn’t ask consumers to pick the different ingredients for their cereal, but rather asked them questions such as “Do you like nuts?” or “Do you want to lose weight”, and then gave the users recommendations based on that. This is a new twist on the idea of a configurator: Rather than letting the consumer really design their own, you create a product for them that they can then alter. That is also one of the reasons why NikeiD is so successful: People start customizing when they find something in the standard catalog that they kind of like - with NikeiD they can make it truly perfect.

So, here are the lessons from the panel:

LESSON ONE: Make it simple

Pandora realized that the radio is an inherently simple experience: You press a button, and you get music. They had a lot of ideas for features and more control for the user over time, but found that it was important to keep the experience simple and accessible to all users. I think that translates into customization - don’t ask your consumers to do too much “work” before giving them anything (or at least try to make it really seamless and fun!)

LESSON TWO: Offer both broad and close matches

Not everyone knows yet what exactly they want. YouTube found that most of the searches on the site are broad, and so in their recommendations on what to “watch next”, they both give close matches to the content of the video as well as broad matches to the overall thematic cluster or the type of video. So as I’m thinking of cereal recommendations, I imagine a cereal that exactly matches your preferences, as well as one that has maybe been created by a nutritionist, that’s very delicious but maybe doesn’t have all the ingredients you indicated beforehand.

LESSON THREE: Provide users context why you recommend what

You could have a black box (as in: a complicated algorithm) that spits out recommendations that you want your users to eat without asking questions. Both Pandora and StumbleUpon however recommend to keep it comprehensible to the user why you recommend what - not only because users like that more, but also because they found it easier to innovate and keep making it better by keeping it traceable. All of the companies found a way to measure how successful their recommendations were.

LESSON FOUR: Make it social, but not too social

Social recommendations are for example when you connect to Facebook, and now the cereal mix that you see has been liked by a friend. Or the cereals mixed by friends just rank higher on the list of recommendations that the user gets. This is a great marketing tool: Not only does it build trust in the product (it’s easy to show data that people are more likely to click on something they friends “liked”), it’s also a starting point for a conversation with a friend, enforcing the connection to the brand or product. Also, in a weird way, influencers are turned on by the fact that no one has liked something yet - they feel that they discovered something valuable that they can share with their friends.

At the same time, the panelists stressed the importance of serendipity, and they suggested not getting all recommendations from a social graph - because then users won’t get the “really wacky things” as often.

LESSON FIVE: Tom Conrad is funny and insightful

Tom Conrad, the CTO of Pandora, is hilarious. He’s also extremely insightful, and one of the thought leaders in personalization. Follow him at @tconrad on Twitter and go to a panel if he’s talking - I first met him at the Mass Customization Conference at MIT in 2010, where he was a fellow presenter.

Want to get started?

All the panelist companies are building their own native recommendation engines, but if you want to plug into an existing taste graph, they recommend Hunch. 

2:41pm  |   URL: http://tmblr.co/ZEiMQy6YGYkQ
(View comments) 
(Notes: 11)
  
Filed under: Personalization Recommendation Engines Pandora YouTube SXSW 
April 19, 2010
An Utopia: Personalized Internet Everything

Apr 19, 2013

Today I watched a movie - it was fantastic. Netflix just knows what kind of stuff I like to see, especially since they started collaborating with YouTube, Vimeo and Hulu. They know when I fast forward, they know what I watch twice, and all that data feeds into Netflix. Netflix knows I like amazing cinematography and they “borrowed” the idea from that site, whose name I don’t remember, where you could choose your music by picking a color (something like http://musicovery.com/, but that’s not who invented it).

So whenever I turn Netflix on, it asks me “How are you” and from there I can be sure that the three movies it suggests are those I like. It doesn’t take more than three, because I like all of them. At the same time, it feeds the data back if the movie industry just hasn’t made enough movies with great colors or surprising plots, and so they know what’s in demand.

Netflix isn’t the only company that recommends stuff. In fact, everything and everyone is collaboration (like, you know, and interNET), and they know me, if I let them. It all began with Hunch…

I’m on something like 15,793 questions answered with Hunch now. I answered most of those between 2010 and last year, because last year I gave Google permission to use StumbleUpon Data as well as my time spent on sites to analyze what I like and how I am, leveraging the data on Hunch of users like me. Of course Twitter and Facebook data is picked up on it as well, and via Foursquare it also knows what I like in the offline world. Sometimes I still like to answer some questions, it’s entertaining.

Recently, I bought a new trash can. Obviously, trash cans isn’t something I buy a lot, so there’s not much data on me and my trash can buying behavior. But Hunch knows my style, and Google knows I like to buy from sites that look great, unless I can get the same trash can cheaper elsewhere. Thus my Hunchoogle results are dramatically different than those from, say, 2010. I get max 5 results, and I know that I like ‘em. The internet has just become amazingly more simple. When I order on chocri, I only see the toppings that they know I like.

Sometimes I go anonymous on the internet. It’s fun to see what other people like. But there’s so much clutter!

I like new ideas for businesses, and my internet recommendation geniuses have totally picked up on that. Genius - good keyword. iTunes’ Genius is much more than music nowadays (especially after they bought Instinctiv and signed a partnership aggrement with Pandora)… whenever I like something, it conspires with Hunch and StumbleUpon (what do other users like me like) and Google (my past behavior), and analyzes what it probably is that I like about it. Then it analyzes everything (say, websites, books, music, video, product, you name it) to bring up other stuff I probably like. Say I want to go out to eat-  thanks to Foursquare, it knows what I like, thanks to Foodspotting, it knows what to eat. So every time around lunch and dinner time, I get an email with a suggestion either what to make out of the groceries I bought recently (of course the store feeds that info into it), or where to go out to eat. No more yelping needed.

Privacy was everyone’s concern - for about four weeks. If I didn’t want it, I’d just turn it off! And my friends are now in something like ‘castes’ depending on how much I trust them and what I want them to know/ give them access to (think Facebook lists from way back). A positive side effect is that hardly anyone lies anymore- just so tough to keep up with that lie throughout all your systems!

The only thing I haven’t gotten used to is that it’s hard nowadays to meet someone who’s not just like me. Facebook keeps bringing people up who are, well, awesome, but exactly like me! I have to try hard (-> I have to go offline!) to meet someone who disagrees with me and doesn’t have the same trash can as me. Which, come to think of it, there haven’t been many new trash cans developed lately - where did innovation go?

9:51am  |   URL: http://tmblr.co/ZEiMQyVoIaq
(View comments) 
(Notes: 4)
  
Filed under: Personalization Utopia Netflix Hunch Genius Twitter Facebook Google Foursquare Privacy Innovation Future Youtube Vimeo 
Liked posts on Tumblr: More liked posts »