Yandex Uses AI to Tailor Ads to Your Liking

Russian search engine Yandex uses machine learning to identify ads you'll accept

By Kyle Wiggers August 24, 2016

yandex machine learning ads rsz 1img 6748 dxoc

Yandex may not have quite the same name recognition it does in Russia, but the Russian search engine positively dominates its domestic search market — in 2015, it handled 57.3 percent of the country’s web queries.

But while search is the company’s bread and butter, Yandex has branched out in recent years — it offers antivirus software, a real-time bidding platform, a topographical mapping solution, language translation, and more. And this week, it dipped a toe into yet another territory: user feedback interpreted by machine intelligence.

Yandex said the new technology, which it began rolling out on Tuesday, is an attempt to build a “better relationship” with its users. It’s debuting in the form of a complaint button within its web browser for Android. When a user see an annoying, obtrusive, or otherwise offensive app, a tap of the new button will flag it for Yandex’s review. The search giant’s servers then “initiate” a custom-tailored ad filter that, using machine learning algorithms, tailors future ads to the user’s tastes.

This is not dissimilar to the concept of an “ad whitelist,” a hallmark of software like Adblock Plus that permits “known good” advertising networks to punch through ad-blocking barricades. But unlike conventional whitelists, Yandex’s technology takes into account individual preferences — the company notes that users can signal particular ads they dislike.

Yandex sees potential in the tech beyond personalized experiences. It thinks advertisers stand to benefit. “[Such technology could] create more targeted and effective campaigns that are relevant to users, reducing the need to install ad blocking software,” it told TechCrunch. Yandex’s accumulated signals, in other words, could help the build campaigns more likely to attract a willingly engaged audience.

“Yandex Browser’s initiative will help all market participants improve current advertising products,” said Dmitry Popov, head of Yandex’s Advertising Network, in related a statement. “[It will] eliminate those that are inefficient and develop those that will be able to provide the best possible customer engagement.”

The AI-powered feedback button is in alpha right now, but Yandex told TechCrunch it plans to expand it to browser clients on other platforms in the future. In total, the browser counts more than five million active users among its ranks, Yandex said.

Yandex, unsurprisingly, is a business heavily dependent on advertising — in the second fiscal quarter of 2016, it derived 96 percent of its total revenue from text-based and display ads. And the web ad business is facing tumult. Juniper Research estimates that ad blocking software will cost publishers $27 billion in lost revenues by 2020, largely as a result of growth on mobile devices: 408 million people used an ad-blocking browser on their smartphone in March of this year.

Publishers have attempted to tackle the problem from a number of angles. This week, Google announced that it would penalize mobile websites that displayed “intrusive” ads to visitors, and earlier this month, social network giant Facebook implemented a new form of display advertising capable of defeating some blockers.

Some publishers have taken measures into their own hands. Slate serves a message to ad-blocking users requesting them to sign up for a premium membership, Bloomberg in recent months has focused on reducing the number of advertisements, and Forbes in December began blocking content from visitors who’ve enabled ad blocking.

Editors' Recommendations