Some excerpts:
To our best knowledge, this work is the first systematic study for [behavioral targeting] (BT) on real world ad click-through [logs].One issue with the study is that it looks only at coarse-grained user segments, at most 160 segments, not fine-grained, one-to-one, personalized advertising. I would suspect there would be added benefit from fine-grained, personalized targeting to past behavior rather than clustering users into large groups. In fact, as Figure 5 in the paper shows, they do not appear to have hit the point of diminishing returns even on splitting into more segments.
[We] empirically answer ... whether BT truly as the ability to help online advertising ... how much BT can help ... [and] which BT strategy can work better than others.
We observe that the users who clicked the same ad can be over 90 times more similar than the users who clicked different ads .... [which verifies] the basic assumption of BT.
We observe that .... the ads CTR can be improved as high as 670% by the simple user segmentation strategies used for behavioral targeted advertising .... [More] advanced user representation and user segmentation algorithms [yielded improvements of] more than 1,000%.
Through comparing different user representation strategies for BT, we draw the conclusion that user search behavior, i.e. user search queries, can perform several times better than user browsing behavior, i.e. user clicked pages. Moreover, only tracking the short term user behaviors are more effective than tracking the long term user behaviors.
Another issue is that they explicitly did not look at using demographic data or locality. It is possible that many of the BT user segments might be grouped roughly by locality, having derived it from search or browsing behavior. If that is true, then much of the gains they saw from BT could be reaped much more easily by targeting the ads to implicit local information. And, if we target to locality, then the additional gains we could expect from behavior targeting then might be much smaller.
But, limitations aside, it is a great paper. The authors clearly and cleanly state their key question -- what is the value of behavioral targeting for advertising? -- and then analyzes a massive historical log to convincingly derive the likely value. It also provides much guidance for those who might seek to build these or similar systems.
The paper has an interesting conclusion that recent search queries are the most useful indicators of people's interests when targeting ads. Yahoo's Andrei Broder said something similar recently when thinking about targeting advertising. It is also worth noting that others who were looking at the value of personalized search came to similar conclusions ([1] [2]).
For more on fine-grained personalized advertising, please see my earlier posts, "What to advertise when there is no commercial intent?" and "A brief history of Findory".
3 comments:
To me, personalized advertising would include, weighted very heavily, the explicit data that can be collected via a simple web interface allowing the user to state current advertising preferences.
It comes as no surprise to me that recent search queries give better results than historic browsing behaviour. Consumers nowadays generally go and search for what they want to buy.
I'd like to see an app developed that gives consumers total control over what ads they see online. As a consumer... as a Human, I don't like being 'targeted'. I don't think anybody likes it.
Give consumers control, allow them to target the products, services and brands they want, and click-through rates should skyrocket to a new plateau.
I completely agree, Jon. Any attempt to do this should make it easy to customize, override, correct, and disable the targeting.
I think the goal of behavioral targeted advertising should be to make advertising useful, helpful, and relevant. Anyone who finds this kind of targeting unhelpful should be able to easily turn it off.
That being said, current untargeted advertising is rarely useful or relevant, nor does it treat people as being individual human beings. We are nowhere near the point where people see advertising and then often think what they saw was helpful.
Thanks for the link to the article Greg.
I'm in BT for OA as well and I find the paper very well written. I have rarely read a so readable technical paper.
The only point which is dark for me, as you pointed, is that they are not making 1-to-1, rather 1-to-k segments of users. I'm using the 1-to-1 approach and the first advantage I see is that you avoid the clustering problem (which algo, nb of clusters, etc.).
I was also surprised by the time scale, I'm using 14 days (two weeks), but I may try less as they propose.
Post a Comment