Adap.tv’s Patented Conversion Tracking Brings Accountability and Measurability to TV Advertising

By Brendan Kitts, Chief Scientist, Adap.tv

Conversion attribution on the Internet is ubiquitous, and many methods – including “last click” and cookie-based matching – are used to match a conversion event back to the initial search or banner ad that the user saw or clicked on.

This technology is seamless, automated, and taken for granted: marketers just drop a conversion tracking script onto their websites, and, presto, they have conversion counts and rates for their various ads.

The widespread availability of conversion data has arguably led advertisers to be able to confidently optimize their ads online with a greater degree of granularity than ever before. Different ad creatives, devices, mediums, keywords and times of day can all be used in optimization using conversion data that has been collected on them. Indeed, one could argue that conversion-tracking systems – with their incredibly fine measurability – have been the engine that has powered the online advertising revolution.

In contrast to online, conversion measurement in TV is nothing short of an unsolvable labyrinth for advertisers. When an ad airs on TV, conversion events can happen on the Web, over the phone and even retail stores; and there’s no way to know whether those sales were driven in part to the original TV ad, let alone what particular TV airing caused it.

With the goal of bridging that gap, Adap.tv has been hard at work in aligning television closer to digital within attribution modeling. Today, we are happy to share the news that the US Patent and Trademark Office (USPTO) has granted Adap.tv an important patent for TV conversion tracking.

This patent validates our work in solving a critical problem for marketers: Online advertising systems have a problem with over-attribution. They tend to be very good at taking credit for – well – everything! TV has the opposite problem; TV tends to take no credit at all.

For example, because online advertising systems are often designed to attribute everything that is last click, it is not uncommon to see branded search keywords (eg. Verizon.com) with an amazing cost-per-acquisition in the pennies thousands of conversions. At this kind of incredible cost-per-acquisition, shouldn’t a marketer just shut off all other marketing campaigns on TV, radio, etc. and pour those budgets into online keywords?

Experienced marketers know that such an approach is likely to result not only in a bloated keyword campaign, but could also spell the end of their business by shutting off one of the most important parts of the sales funnel – people who need to learn about and be exposed to the product for the first time.

The reality is the people who typed in the brand’s name into the search box overwhelmingly already know the product’s name and what it does. The paid keywords are being used as navigational links to reach the site. To put it bluntly, keywords can receive credit by simply being in the right place while a user’s navigating to the site. It’d be like a promoter going up to fans waiting in line to get into a concert, giving them a coupon, and then claiming credit for the fans walking through the door. (Recent reports corroborate this phenomenon.)

This dichotomy between over-attribution in digital and lack of quantitative data in television makes it extremely difficult for marketers to calculate how much budget to apply towards TV. Further increasing the difficulty, the lack of granular conversion tracking also makes it impossible to do things like optimize TV media towards the media that is producing the highest number of conversions. In a media environment where every dollar counts, this can be incredibly wasteful.

This patent describes one of Adap.tv’s automated conversion tracking systems for television, designed to go beyond last click-type attribution to credit assignment based on properties of the conversions and media event. US 8,768,770 “System and Method for Attributing Multi-Channel Conversion Events and Subsequent Activity to Multi-Channel Media Sources” describes a process where a machine-learning system is trained to recognize conversions that come from TV, based on cases which are clean enough for deterministic attribution – often about 1% of the cases. It then estimates the probability of conversion for the larger set of TV airings based on those learned patterns between airing and conversion.

The technique makes it possible to probabilistically separate organic Web activity from Web activity driven from TV. This kind of signal source separation is similar to the “cocktail party problem,” where one tries to segment specific conversations out of several conversations happening simultaneously within a room. The system can also report on conversions that are due to marketing events that were not TV – For example it would be equally bad to over-assign credit to TV for understanding which TV airings have been more effective – in order to do this, not assigning credit is just as important for optimization purposes as assigning credit.

Adap.tv has worked diligently to disambiguate, measure, and report on TV’s impact and make it possible to budget TV in a rational way. Adap.tv and Convertro, the leading multi-touch attribution platform recently acquired by AOL, have years of experience running television campaigns and measuring television sales response. In general, our results suggest that TV effects are extremely large, distributed across multiple channels, extended in time, and are woefully under-reported.

With better measurement techniques, we believe that it will be possible to bring hard ROI measurement to TV and put it onto a similar footing as online advertising. That’s good for everyone, not only in television, but also in online advertising too. Optimizing your marketing campaign using keywords only is equivalent to looking for your keys by only searching under a street lamp – just because there is some light there, doesn’t mean that’s where you should be focusing.

The objective should be to cast light on all parts of your marketing campaign.

Further Resources
Read the patent contents here: http://bit.ly/1oCejXA

A scientific paper on the algorithm was published at IEEE International Conference on Data Mining, along with attribution results from various television advertisers. You can read that paper here: http://bit.ly/1zpDXEE

Conversion attribution on television, radio, offline, and digital channels, is performed by Convertro who use a multi-touch attribution (MTA) algorithm to measure effects across channels. You can learn more about Convertro’s technology at www.convertro.com.

By Sean Crawford, Vice President, Global Head of Inventory at Adap.tv

The annual Internet trends report from Mary Meeker, a partner at venture firm Kleiner Perkins Caufield & Byers (KPCB), has predicted the growing importance of mobile over the past several years, but this year’s report put mobile’s future into clearer focus: mobile internet traffic is growing at a rate of 1.5 times that of conventional broadband, and at an annual rate of 81 percent. Video, she says, is largely driving that growth.

It’s clear that people are watching video on a whole host of connected devices and mobile is a central part of our lives today. With the advent of this explosive consumption of video through mobile applications, there is an even greater needed to accurately measure those growing audiences.

Nielsen has been a company leading that effort, testing an expansion of its Online Campaign Ratings to mobile. This would mark the first only only measurement solution to offer insights into a campaign’s full digital and cross-platform audience.

We are excited to announce that Adap.tv’s platform is a certified partner with Nielsen’s Online Campaign Ratings for mobile, expanding on our multi-year relationship with Nielsen in video measurement. We already work closely with Nielsen delivering the latest in audience guarantee technology and this in another powerful tool for our clients.

Mobile will continue to see rapid growth and brands are starting to invest in it as a critical component within their overall marketing strategy. Similarly, advertisers are looking for ways to substantiate investment and effectively measure campaign impact. It’s not enough anymore to simply measure the impact of a campaign across one or two devices.

Cross-screen and integrated measurement needs to be comprehensive and thorough, and Adap.tv’s clients will be able to activate unbiased, third-party measurement through our expanded mobile partnership with Nielsen.

We are currently conducting a pilot program with clients, and will have additional news to share in the future.

For more information about Adap.tv’s certification with Nielsen’s Online Campaign Ratings for mobile or to inquire about a pilot program, please reach out to our team today.

http://blog.adap.tv/2014/08/12/2339/

Adap.tv State of the Video Industry Survey Sweepstakes Offical Rules

No Purchase Required to Enter or Win

Eligibility: The Adap.tv Sweepstakes (the “Sweepstakes”) is open only to legal residents of the 50 United States (including the District of Columbia) and Canada (excluding Quebec) who are 18 years of age or older at time of entry. Employees of AOL Inc., its advertising or promotion agencies, those involved in the production, development, implementation or handling of Sweepstakes, any agents acting for, or on behalf of the above entities, their respective parent companies, officers, directors, subsidiaries, affiliates, licensees, service providers, prize suppliers any other person or entity associated with the Sweepstakes (collectively “Sweepstakes Entities”) and/or the immediate family (spouse, parents, siblings and children) and household members (whether related or not) of each such employee, are not eligible. All U.S., federal, state and local and Canadian federal, provincial, and municipal laws and regulations apply. Void in Quebec and where prohibited by law.

Sponsor: The Sweepstakes is sponsored by AOL Inc., 770 Broadway, New York, NY 10003 (“Sponsor”).

Agreement to Official Rules: Participation in the Sweepstakes constitutes entrant’s full and unconditional agreement to and acceptance of these Official Rules and the decisions of the Sponsor, which are final and binding. Winning a prize is contingent upon fulfilling all requirements set forth herein.

Entry Period: The Sweepstakes begins at 9:00 AM ET on July 23, 2014 and ends at 6:00 pm ET on August 8, 2014 (the “Entry Period”). Entries received prior to or after the Entry Period will not be accepted.

Entry: Go to https://www.visioncriticalsurveys1.com/S.aspx?s=883&r=UFk2wKERrU6HVCnR5EBS_A&a=1266&fromdetect=1 and follow the instructions to submit your entry. Limit one (1) entry per person. The use of any agencies or automated software to submit entries will void all entries submitted by that person.

Drawing: At the conclusion of the Entry Period, Sponsor will select the name of one (1) potential Grand Prize Winner in a random drawing of all eligible entries received during the Entry Period. The odds of being selected as a potential winner depend on the number of eligible entries received during the Entry Period.

Requirements of the Potential Winner: An entrant who is notified that their entry was selected in the random drawing is a Potential Winner. Potential winner will be contacted via email and will be asked to provide their full name, age and mailing address within a specified time period. If a potential winner does not respond within the timeframe stated in the notification, the Sponsor may select an alternate potential winner in his/her place at random from all entries received during the Entry Period. A Potential Winner is not a winner until they have returned all required documentation and eligibility has been verified by Sponsor. Potential winner must comply with all terms and conditions of these Official Rules, and winning is contingent upon fulfilling all requirements. Except where prohibited, Potential Winner may be required to sign and return to Sponsor, within a specified timeframe to be determined by Sponsor, an Affidavit of Eligibility, Liability/Publicity Release and W-9 form in order to claim her Prize. Failure to return documents as specified, or if prize notification is returned as undeliverable, will result in the entrant being disqualified, and the prize may be awarded to a potential alternate winner. In the event the potential winner of any prize is a Canadian resident, he/she will be required to correctly answer a time-limited mathematical question to be administered by email/mail to receive the prize. Acceptance of a prize constitutes consent to use winner’s name and likeness for editorial, advertising and publicity purposes without additional compensation, except where prohibited by law.

Prize: One (1) Grand Prize Winner will receive an AMEX gift card in the amount of $250 USD. Gift card is subject to issuer’s terms and condition.
Prize is not transferable and no cash or other substitution may be made, except by the Sponsor, who reserves the right to substitute a prize with another prize of equal or greater value if the prize is not available for any reason as determined by the Sponsor in its sole discretion. The winner is responsible for any taxes and fees associated with receipt or use of a prize.

General Conditions: In the event that the operation, security, or administration of the Sweepstakes is impaired in any way for any reason, including, but not limited to fraud, virus, or other technical problem, the Sponsor may, in its sole discretion, either: (a) suspend the Sweepstakes to address the impairment and then resume the Sweepstakes in a manner that best conforms to the spirit of these Official Rules; or (b) award the prize at random from among the eligible entries received up to the time of the impairment. The Sponsor reserves the right in its sole discretion to disqualify any individual it finds to be tampering with the entry process or the operation of the Sweepstakes or to be acting in violation of these Official Rules or in an unsportsmanlike or disruptive manner. Any attempt by any person to undermine the legitimate operation of the Sweepstakes may be a violation of criminal and civil law, and, should such an attempt be made, the Sponsor reserves the right to seek damages from any such person to the fullest extent permitted by law. The Sponsor’s failure to enforce any term of these Official Rules shall not constitute a waiver of that provision. In case of a dispute as to the owner of an entry, entry will be deemed to have been submitted by the authorized account holder of the email address associated with the entry.

Release and Limitations of Liability: By participating in the Sweepstakes, entrants agree to release and hold harmless the Sweepstakes Entities from and against any claim or cause of action arising out of participation in the Sweepstakes or receipt or use of any prize, including, but not limited to: (a) unauthorized human intervention in the Sweepstakes; (b) technical errors related to computers, servers, providers, or telephone or network lines; (c) printing errors; (d) lost, late, postage-due, misdirected, or undeliverable mail; (e) errors in the administration of the Sweepstakes or the processing of entries; or (f) injury or damage to persons or property which may be caused, directly or indirectly, in whole or in part, from entrant’s participation in the Sweepstakes or receipt of any prize. Entrant further agrees that in any cause of action, the Sweepstakes Entities’ liability will be limited to the cost of entering and participating in the Sweepstakes, and in no event shall the Sweepstakes Entities be liable for attorney’s fees. Entrant waives the right to claim any damages whatsoever, including, but not limited to, punitive, consequential, direct, or indirect damages.

Disputes: Except where prohibited, entrant agrees that any and all disputes, claims and causes of action arising out of, or connected with, the Sweepstakes or any prize awarded shall be resolved individually, without resort to any form of class action, and exclusively by the appropriate court located in the Commonwealth of Virginia. All issues and questions concerning the construction, validity, interpretation and enforceability of these Official Rules, entrant’s rights and obligations, or the rights and obligations of the Sponsors in connection with the Sweepstakes, shall be governed by, and construed in accordance with, the laws of the Commonwealth of Virginia, without giving effect to any choice of law or conflict of law rules (whether of the Commonwealth of Virginia or any other jurisdiction), which would cause the application of the laws of any jurisdiction other than the Commonwealth of Virginia.

Sweepstakes Results: Sweepstakes results may be obtained by sending a hand-printed, self-addressed, stamped envelope to Adap.tv’s Sweepstakes Winner, c/o Adap.tv, 1 Waters Park Dr., Ste 250, San Mateo, CA 94403. All requests must be received by September 30, 2014. Canadian residents may omit return postage.

What You Missed From Adap.tv’s Global Product Webinar

A few weeks ago, we hosted a global product webinar covering the latest innovations around our new yield optimization and brand & creative control features.

In this exclusive webinar, we shared compelling use cases from our publisher and ad network clients that participated in our yield optimization beta launch program. They were able to dramatically increase fill rate and optimize revenue opportunities on each impression.

We also illustrated new brand controls that ensure publishers that their brand integrity is preserved by controlling what creative assets they choose to accept or reject.

We had a lot of great questions from both existing and prospective clients, and we are highlighting three in particular:

Why do some in the industry use parallel ad calls?

Our approach to yield optimization is drastically different to our competition. We prefer server side yield optimization and leverage machine learning algorithms to learn what ad that has the highest expected revenue based on the inventory source and device combination. Parallel ad calls, on the client side, can heavily degrade the end-user experience and increases latency.

Instead of parallel ad calls where you rank all ads and only give the opportunity to show to the top 7 purely based on price, we rank all ads based on the expected revenue (ad success rate * CPM) and try sequentially the best ad first. We could do parallel ad call but we think this is in detriment of the end-user. Our server side yield optimization effectively maximizes publisher revenue without degrading the end user experience.

Can you give an example of brand control within competing ads?

Let’s take the following example: Suppose your direct sales team goes out and sells your homepage inventory over the holiday season for AT&T. But, AT&T has stated that want the exclusive and don’t want to see any other telco brands. As a publisher, you need to be able to enforce that.

In addition, if you are also selling other inventory programmatically, you need to be able to guard against competitor creatives. With our brand and creative control tools, you are able to easily approve or reject creative assets in order to maintain to contractual relationships.

What are some of the factors that attribute to a reduction in ad errors?

We rank ads by success rate, so innately you will see a reduction in ad errors. We are looking at a historical success rate of a particular ad from a 24hr period. If we didn’t review ad success rates within a 24hr period, there could be a high price ad that might be misconfigured or set up with a high price but a low success rate.

This type of ad might be tried continuously without success – driving those latency factors we discussed. With the fill rate optimizer, your ad error report will look a lot cleaner, dropping low success rate ads to the bottom.

[Video] Ad Buyers from MAGNA GLOBAL, Xaxis and Universal McCann Want Linear TV Sales To Go Programmatic



Last month, executive leaders from MAGNA GLOBAL, GroupM’s data division Xaxis, and Universal McCann spoke at Beet.tv’s summit on programmatic TV advertising presented by Adap.tv. The topic: linear television and the adoption of data-driven, highly-targeted techniques to drive greater value for advertisers and programmers alike.

Adap.tv and ONE CEO Toby Gabriner added: ”The notion of using data and starting to move in and out of inventory in near-time is starting to happen – agencies are starting to wake up to the power of that. It’s being drive a lot by clients (like P&G) who sit on mountains of data.”

Watch out the session video above for more.

Bringing Greater Precision to TV Advertising: Welcoming PrecisionDemand To The Family

By Toby Gabriner, CEO of Adap.tv and ONE by AOL

One would only have to look at the quality of content rolled out at this year’s Digital Content NewFronts and the TV Upfronts to understand that the future of video is TV and digital, not just one or the other. Digital video content is looking more and more like TV, and TV planning and measurement is looking more and more like digital video. The lines are quickly blurring.

As viewers continue to migrate across more screens and platforms – whether it is a PC, a smartphone, a tablet, a TV connected to an Xbox, or broadcast and cable TV – the ability for marketers to reach, engage and measure advertising against those audiences has become more challenging, even more so when considering the silos separating TV and digital advertising.

To address this issue, Adap.tv announced the addition of linear television to its programmatic buying platform earlier this year, providing marketers the best of both TV and digital – the ability to transact against traditional age/gender demographics, and automatically optimize ad spend using customized, more precise audience segments – across all screens.

Today, AOL is taking another important step forward in continuing to build its platform capabilities around TV and digital video by bringing PrecisionDemand into the family.

Integrated into Adap.tv’s programmatic buying and selling platforms and, eventually, ONE by AOL, PrecisionDemand will be a key component of our advanced TV targeting, attribution and optimization technology available in the market.

For customers, this means a new and robust methodology that connects consumer purchases back to specific TV ad buys, not just the usual media mix modeling that is used today. Marketers can see the true value and have a deeper understanding of their TV and cable ad commitments beyond traditional age/gender metrics, such as the effect advertising against specific dayparts or networks has on consumer purchases.

More specifically, customers will be able to:

  • Onboard first-party advertiser data, auto-enrich with more than 400 attributes, anonymize and cluster to create a highly customized target profile;
  • Score TV media assets, such as programs or airings, to produce targeted media datasets customized to that target profile;
  • Automatically generate a targeted media buy plan and execute that plan via a programmatic TV marketplace or through direct sales channels
  • Integrate advertiser data and measure the response to media, feeding results back into scoring and media planning for optimization.

The advent of new screens and viewing platforms has necessitated automation technologies that can effectively use data to better plan, reach and measure those fragmented audiences and tie publishers’ and marketers’ efforts across TV and digital together.

With PrecisionDemand now on board at AOL, we are greatly accelerating our efforts in creating the platforms needed to manage today’s multiscreen video world, through Adap.tv today, and soon through ONE by AOL. The opportunity here is immense; we at AOL have built and collected the assets to take advantage of it, and I am excited by the challenge of unlocking our potential.

 

Making Yield Optimization Work for All Video Publishers

Publishers often experience the headache of discovering that their yields are lower than expected — ultimately, preventing them from hitting their revenue goals.

Yield optimization is not a new concept, but it’s still an incredibly important component of the selling process, whether you are a premium publisher that uses a direct sales team or a publisher that uses third-party demand sources. In either instance, you cannot afford to wait and retroactively discover that an ad has had lackluster performance — you want to automatically identify ad sources that are and are not performing and act in real-time.

To that end, the latest yield optimization enhancements in Adap.tv’s Demand Path platform activate machine-learning algorithms to ensure that you make the most money from every single impression, every single time.

We do this by not just simply analyzing pricing. Traditionally, multiple ads are called and are ranked by price, with the hope that one delivers. However, doing so can potentially impede publishers from missing out on good ad opportunities and will impact latency, user experience and potentially lead to lost impressions. Demand Path will only try ads that have a proven track record of recent success, so that you can get more ads to your users, faster.

Further, Demand Path’s yield optimization provides a 24-hour success rate tracking system, which automatically ranks ads in order of expected revenue and ensures you get higher success rates, higher CPMs and lower latency. This gives publishers additional flexibility from existing solutions that use a 72-hour window and limits responsiveness only to an ad’s most recent performance.

Lastly, our yield optimization enhancements differ from traditional, parallel ad calls. Parallel ad calls simply try the first four ads, ranked by price. Adap.tv will try one ad at a time and will always try the most optimal ads first.  This eliminates time wasted by making four simultaneous ad calls, when one or two can more quickly serve an ad to the viewer.

So, how does this technology really work? It’s quite simple: automatically and comprehensively. Instead of just responding to a seller’s request with a daisy chain of ads ranked by price, Demand Path’s yield optimization gives the seller another critical dimension in success rate percentage. Sellers can see their ads prioritized by expected revenue, which efficiently weights the ad price multiplied by their delivery success rate for that specific inventory in that specific seller media property. Over time, Demand Path can learn the performance of an ad for specific inventory sources, including specific device types, and use this information to rank the ads in the daisy chain.

We have rolled out the enhancements to yield optimization for all of our Demand Path clients, and we encourage you to see how they have already improved your fill rates. Our mission is to give our publishers better data on the value of their inventory and the insights required to drive optimal ad revenue.

Our new yield optimization works seamlessly across both direct and programmatic demand sources in either public or private marketplaces.

Here is what a publisher client had to say about Adap.tv’s enhanced yield optimization:

“When we implemented Adap.tv’s yield optimization tool, we saw improvements in our business — in both revenue & workflow. This new tool helped our team to prioritize ads on more than just priority and price. By analyzing ad performance across multiple dimensions, we improved our overall fill rate, and our success rate went up by 3%, minimizing wasted impressions. In addition, we reduced ad errors, allowing for more inventory and impressions to sell.”

For more information about yield optimization on Adap.tv’s Demand Path, please contact your Adap.tv client services representative or email us at publisher.platform@adap.tv.

Adap.tv Achieves Certification for IAB’s Quality Assurance Guidelines 2.0

IAB Quality Assurance Guidelines 2.0Today, the Interactive Advertising Bureau announced an update to their Quality Assurance Guidelines (QAG), which help establish trust between buyers and sellers in a complex and ever-changing digital advertising ecosystem. Adap.tv is a proud and active participant in the initiative and has been certified under QAG 2.0 to ensure brand safety and combat piracy.

Adap.tv shares the mission of the QAG program of reducing the friction and fostering an environment of trust in the marketplace. As the technology provider for both advertisers and publishers, Adap.tv uniquely understands the importance of trust in the buyer-seller relationship. QAG offers a common language that allows publishers to more easily demonstrate a new level of excellence in trust, transparency, quality and safety, and advertisers to make informed decisions with their media investments.

Certification under QAG 2.0 is another step in Adap.tv’s commitment to brand safety, Advertising Assurance. (Read our recent post about Advertising Assurance here.)

Please visit the IAB’s website for more about the IAB Quality Assurance Guidelines.