Posts Tagged ‘Online Personalization’

July 10, 2015

Targeting Mismatch

Personalized Re-targeting is a type of advertising designed to turn would-be customers into actual customers, by showing the would-be customers products they previously expressed interest in. You may have noticed that some products and merchants seem to follow you around the internet. You may have viewed a product on one website and then noticed an advertisement for the same product on another. Advertisers are hoping to lure you back to their site to complete the transaction by reminding you of products you previously looked at. After all, you must be at least a little interested in the product to have viewed it the first time. Or so their logic goes.

Personalized Re-targeting has been around for years. I’ve encountered this behavior before back in 2011. Only then re-targeting made sense. The past few weeks the re-targeting I’ve witnessed has just been a waste of advertiser dollars.

Domingo and I are in the middle of furnishing our new home. High on that list was a new dinning room table. I spent a few days browsing different tables online before making a purchase. For the next week my facebook feed was filled with ads, not just for the table I purchased, but for the other tables I viewed as well. All from the same merchant. “Still on your mind?” the caption for one ad reads. “Don’t let this one slip away!” reads another. I didn’t. I had made the purchase.

I suspect it’s extremely rare for someone to purchase the same dinning room table from the same merchant in two transactions over a short period of time. If I’m being generous I would assume it’s slightly less rare for someone to purchase two different dining room tables from the same merchant in two different transactions. The ad broker monitoring my behavior and tracking me as I viewed all those dinning room tables should have also noticed I added one to my cart. But no. If the ad broker did observe the check out process, they decided to remain blissfully ignorant of the transaction. As a result I’m shown ads that don’t interest me. It’s not only annoying to the consumer, it wastes the merchant’s ad dollars.

This afternoon I purchased a kitchen table. My news feed is once again filled with advertisements featuring the new table. Same problem but different product and different merchant.

I’m all for personalized advertising. (Yes, please do help me find good area rugs that go with the furniture I’m purchasing!) Targeting advertising doesn’t have to be a nuisance. In order to not be a nuisance, however, it’s going to have to get a bit smarter.

May 26, 2011

The Filter Funnel

There was a Ted Talk by Eli Pariser that’s been getting a lot of buzz called the “Filter Bubble”. The concern is that with an emphasis of personalization on the web (personalized search results on Google, personalized news feeds on Facebook, etc) that we as individuals only see some small part of the web. As a side effect of personalization, we are only exposed to things that are familiar and pleasing to us. The concern is if Google learns I lean left or right, it only serves me content that confirms my beliefs. We never are exposed to contrary ideas. In effect, we can’t learn.

I disagree with Pariser. I can’t speak to facebook, but as a researcher in personalize search I think Mr. Pariser misses the point. He makes three arguments: (1) The search engine “hides” or filters out information to the user; (2) The search engine has a duty to inform the user of all relevant information, including information the user may not want; (3) users are unaware that they are missing information.

The first point is just flat wrong. In a personalized approach, search results tend to be re-ranked – not hidden. In Mr. Pariser gives an example of two of his friends search results for the query “egypt” during the protests. He only shows the top 5 or 6 search results for two different users. If you go deeper into the search results, you’ll likely find the same results, just at different ranks. Results are not hidden, the user just may have to dig deeper to find them. Ont can argue that most users don’t look beyond the top couple of results, but that’s not the same thing as hidding results.

The query “Egypt” is a very ambiguous query. The search engine is trying to guess what the user is likely interested in (travel, demographics, politics, etc). The user who sent him one screen shot void of protest information may not care about politics in the slightest. But if he did want those search results, it’s simple enough to reformulate the query. Think of the search engine as a pizza parlor you frequent. When the guy behind the counter sees you, he may put the special you always order in the oven, even before you get to the counter. That doesn’t mean you _have_ to order that pizza, or that your doomed to the meat lovers delight for the rest of your life, it just means you have to specify that you want something other than the usual. The same thing is true with the search results. You don’t have to accept the first results as the only information available, and users often don’t. Reformulating queries to get better results is extremely common.

This brings us to the corner stone of his argument is point, that the duty of the search engine. Mr. Praiser tends to equate the search engine with news, saying there is a duty to provide full accounts of information to the user. Really it’s more likely a library, where the user uses the card catalog to find information he or she wants. The search engine is an aggregator of information, not a disseminator; the user seeks out information from the search engine, the search engine doesn’t push information to the user.

If the user is not receptive to new information, then trying to force it on the user is counter productive. Mr. Praiser argument makes the assumption that if the search engine provides a more complete picture, the user will accept all relevant information. Visiting cnn, msn, fox news and reading the comments, shows people are finding their way to content they disagree with, and can continue to turn a blind eye to inconvenient facts when presented with them. This is not a new phenomena. It’s a form of confirmation bias (accepting things as truth when fit your beliefs regardless of facts), and human nature to discount things that don’t match our view of the world. Thus the “Filter Bubble” is more of a “Belief Bubble”.

This brings me to my final point, and the reason why I called this post the “Filter Funnel” – Personalization has been shown to increase serendipity in search (the discovery of new things.) I often see this in my own research, as well as published works by others. Often when an individual searches, they only consider the top search results. Going back to the Egypt query, perhaps I only care about travel, and not about politics. Maybe I am only looking for the airport in Egypt. By re-ranking search results that are likely not of interest to me, I see more search results that may be of interest within each snapshop. More relevant results tend to lead to the discovery of more information that is useful and fits my need. Perhaps the first result has the name of the airport, but the next three have valuable information about travel to Egypt that I wouldn’t have thought to search for. I now have more information of value to me than I would have had the results not been personalized.

This isn’t to say that over personalization isn’t a problem. I don’t like the news filtering on Facebook for much the same reason as Mr. Praiser – Just because I don’t interact with statuses from a subset of my friends doesn’t mean I don’t enjoy reading them. That’s a failure of the algorithm to identify what is interesting, but that doesn’t mean filtering in general is wrong. After all, there are also a subset of statuses on facebook I am much happier to have never read.

We can’t expect the tool to replace our own due diligence. If the user doesn’t want a complete picture, or both sides of the argument, than no amount of “ought to”s for the search engine will change that. The search engine will always strive to help the user arrive at valuable information as fast as possible. We may disagree, however, on what information is valuable.

In theory, ordering online is faster than going to the store. For me at least, this is far from true true. I tend to be deliberate and slow, waiting for deals. One trick I employ while shopping online is to log in to the store, add an item in my cart and then close the browser. In the past, I’ve found if I wait just a little while, I’ll get a coupon from the store in hopes that I will complete the purchase. It reminds me of car dealer negations. You’re hiding the fact that you really want the product in hopes the seller will discount the price more. I’ll track products on multiple sites to see if catch any price drops and sales. This kind of price hunting may start to become more delicate.

Many companies are shifting towards more consumer profiling. Capital one made the news back in August when it was discovered they used a third party to estimate a potential customer’s worth. The third party collected data based on where you lived (from your IP address), what type of browser you used, what time of day it is**, etc, to make guesses on how much income you have, and how good a credit risk you are. Capital one would then choose which credit card offers to display on their website based on that estimation. Capital one claimed not to use the data in making lending decisions, however they made the news again six months ago when they offered different users different loan rates presumably based on the browser used. This action is legal because they aren’t discriminating based on any of the protected classes. This kind of profiling, however, is one trend that may make online discount hunting harder.

A product otherwise on sale may be offered to me at full price if the profiler estimates (rightly or wrongly) that I want the product and can afford it. This isn’t exactly new, but it may be becoming more common. Amazon tried something similar, but reversed their policy admit a backlash from the internet community. Although, there are mixed reports that they may be at it again, mostly by redirecting prime customers to different products and not price fixing per se.

This dynamic pricing (Also called flexible pricing, customized pricing, and personalized pricing) has become an increasing concern of mine with the abundance of personalized ads. A few weeks ago I was jewelry shopping on QVC.com. I ended up leaving a tab open because a ring I liked was out of stock in my size and I wanted to see when it would be back in. I’ve now noticed as I’ve surfed the web that the same ring has been featured on ads for QVC. I tried it out by leaving a tab open with a different product. This means several things: 1) QVC (or a third party acting on QVC’s behalf) knows what my shopping behavior is and have tied it to me, likely by the cookie they left on my computer; 2) They are sharing that data with a third party advertiser responsible for display ads on many different websites; 3) The ad broker is likely keeping tabs on where I am going and may be sharing that information back to QVC. What if I purchase something expensive elsewhere, will the advertiser tell QVC that I can afford to pay more? If I look for a QVC discount code, would it signal that I really want the ring so QVC should raise the price? To be fair, I don’t think this is unique to QVC. Nor do I think QVC is doing anything deceptive in terms of price altering. The price never changed for me, and I had my husband check from a different state using a different browser and operating system. My concern is that dynamic pricing will be the next step.

The concern I have is I am no longer in charge of the single I send. I do not know how online companies are evaluating me, and what that could mean to my bottom line. While dynamic pricing has been around for ages in the form of senior citizen discounts, or student discounts, in those cases the change is price is transparent. I know what the discount is, whether or not I qualify and what I have to do to get it. When dynamic pricing happens because of my internet habits, I have no awareness. I don’t know that if I had opened Chrome instead of Firefox that morning, I could have saved. Would a company assume I have more disposable income if I view their website from a smart phone?

There’s no clear cut way to thwart this kind of tracking. Removing cookies would be one step, since it reduces the amount of ongoing tracking most companies can do. Even that’s not full proof, as my IP address is unlikely to change in any one sitting. If the combination of ip geolocation, exact operating system (vista home vs Windows 7 professional, etc), and browser version is not enough to identify my computer, it certainty narrows down the field of possibilities.

For now, I will have to be careful about how I shop online if I want to ensure I am paying the best prices.

** Whether you’re on during the day or night could indicate what type of job you have: day shift vs night shift, white color vs blue color. The type of browser and operating system can also be used for profiling, as computer geeks often use linux, while trendy hipster types might prefer apple.