Give it a Sphinn | Or a 
What follows is my understanding of the stumbleupon algorithm it is based on some pretty extensive testing using several volunteers however it has been incredibly simplified to make it easier to understand. We may be totally wrong so just a heads up but I hope this will at least give you some idea of what your thumb up is doing. I have also written up a few questions and answers to help people understand what I'm trying to do.
Audience score
Every stumbler has an audience score in the old days stumbleupon told you what your score was but have since taken this facility away. The audience score was based on number of fans, number of pages thumbed up, number of pages thumbed down and number of reviews written. The score is what determines how much stumble juice a person carries. The audience score has one other factor stumble history. If a stumbler initially stumbles a site and the site receives a large quantity of thumbs up their audience score increases conversely if they initially stumble a site and it’s thumbed down their audience score goes down. Stumblers who stumble a site after the initial stumble also have changes to their audience score but not to the same extent. It is hard to weight which factor is most important when increasing audience score but the factors as I see them are:
- Number of fans
- Number of thumbs up and down you have given
- Stumble thumb bonus – increase to score based on number of thumbs received on a page.
This model means that the obvious technique to get a “power account” is to find more fans, thumb up loads of pages and start stumbles on pages you expect to be popular – sound familiar its pretty much the same on every social media site. Once we have our idea of an audience score its time to look at a few basic models that stumbleupon might use, you can skip to the big one if you want but these smaller models I think are important to demonstrate individual parts of the algorithm.
A Basic model
Initial stumbler + (number of thumbs up / number of thumbs down) = visitors
This basic model is based on the idea that the initial stumblers audience score will dictate how many visitors will initially see the page and then the number of thumbs up will dictate how many additional people see the page it also presumes that thumbs down have equal weighting to thumbs up.
Audience driven model
Initial stumbler audience + (% of audience of stumbler per thumb up / number of thumbs down) = visitor
This model is a little more complex it presumes that the full audience score is used for the initial stumbler while each additional thumbs up passes a percentage of each stumblers audience score. This model would account for the stumble wave effect, where stumbleupon sends continual waves of varying sizes.
Audience + Domain model
(Initial stumbler audience/#stumbled domain)+ ((% of audience of stumbler per thumb up/#stumbled domain) / number of thumbs down) = visitor
This model presumes the number of times the domain is stumbled by a user is a factor therefore the initial stumblers audience score is affected by the number of times they have previously stumbled the domain. If this is done for both the initial stumbler and all stumblers thumbing the page up or down it would explain why mailing lists and friends stumbling the same domain has less and less effect. The models above show a continual development but there are few more factors rather then showing endless models I will just discuss these factors Friends Being friends is not a bad thing while stumbleupon does not provide a bonus it is my belief it does penalise accounts that continue to stumble the same things without being friends or at least one party being a fan. I do not believe the penalty to be huge just a balancing factor to flag that the accounts routinely stumble the same information. Organic bonus This I think is a huge factor when a user arrives on a site via the toolbar it is “organic” in the way your arrived, stumbleupon presumes you are judging the page on merits having not seen it before it therefore gives more weight to thumbs up that come via organic stumbling. This is another reason mailing lists fail to work over time on stumbleupon. Send to I initially categorised the use of send to as “organic” stumbling but my current belief is that it is not considered organic and therefore does not provide a bonus from organic stumbling, more experiments need to be carried out but I believe it may indeed be the reverse and actually cause a penalty.
The Big one
(Initial stumbler audience /# domain) + ((% stumbler audience /# domain)+ organic bonus – nonfriend) – (((% stumbler audience + organic bonus) + N
So initial stumbler juice is his audience plus his previous stumble bonus which is divided by the number of times the domain has been stumbled by the user. Plus for each thumb up the juice is a percentage of their audience score plus their previous stumble bonus divided by the number of times the domain has been stumbled by that user plus a bonus if the stumble was organic and any to close penalties that may apply. The audience score is reduced by a percentage for each thumb down stumbler plus a bonus if organically stumbled. Finally N which is a random number generator or a Tim get out of jail free card. The big model is simplified to the extreme but I think is fairly accurate but it does not explain stumble wave suitably so within our model we need to look at time. Sadly we haven’t been able to run an experiment beyond a month but based on previous statistical evidence time stumbleupon waves occur on an almost logarithmically with large quantity of waves occurring after the first stumble and then petering out, until the next thumb which sends another series of waves. Lets follow some examples we will use totally fake numbers to make life easy. A stumble upon user Our user lets call him Fred has an audience score of 10 he goes along and starts a new stumble at a site he has never visited it gets a couple of hundred visits and 3 thumbs up Fred gains a point to his audience score for thumbing something up +a further bonus because others liked his stumble so fred now has an audience score of 13 Fred is really impressed that so many visitors came to his site so he thumbed up another page, even with his increased score it didn’t do so well and only 2 people thumbed it up and 2 thumbed it down! His score is now 14 (increased for thumbing up – no bonus ) Fred tries a different domain it does well and 10 people thumb it up his score goes up to 25, Fred has realised stumbleupon can make him money so thumbs up his proxy site it gets a few visitors but 7 people thumb down the site and 2 marked it as spam. Fred audience score plummets (18 but has been marked by spam so temporarily has his score halved) so his score is now 9 poor Fred will have to work hard to regain his score. A Domain Some nice person stumbles the site they had an audience score of 10 which brought a 100 people 3 other people thumbed the site (all came via organic) with scores of 30/100/40 they bring a further 150. Next day the domain is stumbled again but the number of stumbles is much lower, the owner tries to encourage people to visit the site by using the send to button and while there are lots of thumbs few extra visitors other then those he sent the send to to. Mailing lists A secret group of stumblers have a mailing list, they send an email when they want something stumbled. The first time it worked great and large amount of stumbles followed
, the second time it didn’t work quite so well soon the mailing list stumbles are counting for little or nothing. (this happens an awful lot repeatedly stumbling the same domain reduces the chance of a stumble wave next time particularly if people outside of the group are not also thumbing up the groups stumbles. What do you think have we got it right? Wrong? Am I completely off my trolley?
I think you’re absolutely right in your assessment. Subsequent mailings are less effective, consecutive stumbles are less effective… Then you get an initial stumble from a ‘top stumbler’ and traffic rockets! More confirmation that just being a good active stumbler actually works…!
Very interesting write-up Tim, I’ve bookmarked this one to come back to it later. Stumbled aswell.
cheers guys
The initial stumbler has a lot to do with how a stumble behaves but even a top stumbler coming in 3 weeks later can have a dramatic effect on the number of stumbles.
This is a very interesting write up and I have to agree that the initial stumbler factors heavily in the algo. I had a post where the initial stumbler had no friends at all. Despite the fact that subsequently, I got 8 reviews + a small load of thumbs up. It was never shown once on SU. Cheers James PS: Stumbled this article. Keep the great work going.
Very nice post! I just gave you a thumbs up. Keep up the good work.
you tried to solve few things . but think you must have put some light on theword “stumbler” i am not able to get that .
Very interesting Tim. I’m not 100% sure i agree with you on a secret mailing list not carrying any weight. I think the stumbling habits of the members is a much more important factor. If they solely stumble their own pages and only suggested pages rather than actually ‘naturally’ stumbling other ‘3rd party’ pages, they will see little benefit. There is a huge benefit in being an active stumbler though.
@James – The initial stumblers audience is a huge factor as you say quite a few of our experiments when run resulted in null results even when I would stumble immediately afterwards and one particular stumble which had nearly 20 thumbs up had the total of 8 visits from stumbleupon. Interestingly this post which has received a large quantity of thumbs up has very little traffic via stumbleupon. The reason the first few stumblers were people who read the blog and regularly stumble it, now that non regulars are thumbing it its starting build traction. @Ash The secret mailing list really is a non starter its great for helping a new domain out but within a few stumbles it looses all its authority. The best results is to wait for the page to come up organic and then stumble it. I think many mailing lists are fooled into thinking they are working because they see stumbleupon visitors but do not realise it was not there votes but the votes of others that did it. Of course there are exceptions if you were planning on running such a group I would a have a very large user base, have the system select 10-30 at random to send the request to, only send the request after a non member had stumbled it etc… by the time you got such a system running think how many posts you could have made
Nice read Tim, love these deconstructive type posts. Stumbling this, hope you can draw a bit more evidence from any resultant traffic boost!
Very nice and detailed but easy to read article
stumbled yours. I hope you monitor this page stumble statistics for your future stumble articles to share to us.
Hi Rob & Reztar cheers guys, yes we are watching this page but as it stands its not doing very well on stumbleupon at all
I think when I last looked stumbleupon had sent a 100 visitors.
Thanks for this great information. Now I can utilize SU better. Stumbled this page, too!
interesting read.. def. a thumbs up from me! thank you
Hey Tim perhaps it was that ‘mathematics’ term in the headline . I’m not one for overtly clickbaity headlines, but I know a man who is
The lack of stumbleupon activity is because there was no initial stumbler http://www.stumbleupon.com/url/ventureskills.wordpress.com/2007/09/19/stumbleupon-mathematics-for-stumblers/ But the headline was a bit of a mistake given that a search for stumbleupon algorithm puts this blog 3rd
we live and learn
I have seen that no initial Stumbler a few times on my site and have no idea how that actually happens. When I use the toolbar, if I am discovering something I have to give it a review or it doesn’t accept my Stumble
In this case it was down to the misuse of the send-to button, I sent out a send to to a friend to proof read as I had lost her email address, but didn’t initially stumble it myself. So a record was made in the system, but with no initial stumbler. I tried to thumb up and leave a review hoping it would recognise me after I noticed the mistake but to no avail. So if using send-to button make sure the domain is already stumbled
Wow, Tom, this is amazing. I was beginning to wonder whether there really WAS an algorithm in place. The depth of this is pretty darn cool, and I’m more impressed with StumbleUpon than ever. Also makes me think differently about how I’m going to use the service in the future for the greatest effect.
I found your article facinating. But it doesn’t seem to me as if my “thumbs up” has any more pull or “juice” than someone who just started stumbling. (I’m a top 25 stumbler). Perhaps it does and I just am not seeing it. But thanks for the article, I am always interested in these kinds of things.
This was an excellent post. You could teach a semester of this at the university.
Is there any point giving a page a thumbs down rating?
@jana you are
particularly if you are the initial stumbler @Chessnoid this will make up about an hour of a class, however two dissertation papers from students will use some of their work from this project. @snowflake each time you thumb down you pass a percentage of your weight against the thumbs up, its not as greater percentage as a thumbs up but is cumulative so it doesn’t take to many thumbs down to stop a stumble.
Great post on Stumble and how it works. I have had great results but never looked into the make-up of it.
Great article! Stumbleupon was purchased by Ebay and I feel Ebay could make good use of it as a “suggestion” tool for those that might want to opt in to it. In my opinion too much of the web revolves around search. Show me what I might want to see based on who I am , what I like. QVC and Home Shopping “suggest” items that you might like based on themes (jewelry, coins etc) and you never search for a thing. I Truly think a smart model along these lines will be part of the next generation of the web. Marty
Martin you might be right some one sent me some details of what they thought were uses of the stumbling algorithm appearing on Ebay, it would be interesting to see if they can harness the suggestion system on an auction well interesting as long as they don’t use the SU community as the test group in this idea
Interesting. Thanks for that. Now I know how it’s working and why my site isn’t getting seen. xD
Thanks for the great read. It now makes sense as to why stumbleupon really doesnt work for me.
nice research. I’ve always wondered some of the factors that affect stumbleupon. Thanks for doing the help.
This is what I called a page that is stumbled worthy. Haha! Great research and post. I’ve been thinking how come my stumble traffic has been so inconsistent and I think this page helps to solve some mystery. Thanks! Regards, Derrick Tan http://www.learn-internet-marketing-free.com
Nice! One business advantage that StumbleUpon has over Digg is that the results of their formula are hidden. If you make it harder for user X to reach the home page on Digg, user X will notice and be offended. Stumbling happens in the dark, so Stumbleupon can change the algorithm and make hand edits and not get heat — they can avoid the trouble that Digg has had lately… Slick!
I think you’re on the right lines for sure. I think there are other factors taken into account also. I would say “activity” would add to the equation, in terms of interaction with other stumblers, the number of times you hit the “stumble” button. Nice post though and im sure you’ll hit the buzz page with this and get thousands of hits, hope you server is ready
mridout196 – look at the date of the article
It seems to me that the thumbs down button is potentially unfair? As a new stumbler I got the impression that I should use it if I don’t want to be sent similar pages, but from reading this post it seems that I am actually weighting against the page being sent to anyone else? So for example, lets say I get sent a page on American political humour, and a I give it a thumbs down not because I don’t like humour (after all, it’s one of my listed Interests), or because it’s a poor quality page, but because I don’t care about American politics, humourous or not. Am I damaging the chances of this page then being sent to others?
Responses to this post: