Yelp announced this morning that it will begin allowing users to tailor their home page and search results based on their personal preferences.
In other words, if you are a vegetarian, or if you are a parent who generally searches for restaurants for children, you won’t have to re-enter that information every time you search. Instead, you can enter it once and Yelp will prioritize those results going forward.
“In the history of Yelp, this is the first time that two people searching for the same thing from the same context will see different and personalized results,” said Consumer Product Manager Akhil Ramesh.
To do this, users select the “Personalize their experience” option, then choose options on dietary restrictions (whether vegetarian, vegan, gluten-free, etc.), their lifestyle (whether they are parents, car owners, or pet owners. ), their accessibility needs (wheelchair access, gender neutral bathrooms), the types of foods they prefer, and other interests (such as bookstores or date nights).
Once you’ve made your selections, those preferences will start to affect the search results you see. Personalization should be obvious because the results will be identified with “many vegetarian options” or “because you like Chinese food.” The home page will also start highlighting places that it thinks you would like.
In some ways this feels like a long overdue move, particularly when so many other popular apps and websites are already heavily personalized. Shy, is Yelp finally taking this approach now?
On the one hand, Ramesh noted a growing interest in different diets. On the other hand, he said: “We have years and years of unstructured, expressive and quality content, and this content is representative of a real experience with a business. In recent years, our machine learning and artificial intelligence capabilities have grown tremendously, and what it has allowed us to do is create really useful features in addition to the high-quality content that we have. “
Ramesh emphasized that Yelp will focus on using your explicitly shared preferences to shape its results, rather than feeding all of its behavior into an algorithm. After all, he said, “any machine learning algorithm will have tons of biases.”
He described this approach as “the human form”: If you were conversing with a person, “you would not try to assume what the person did over the weekend.” You would just ask the person and you would have an open conversation. “
At the same time, he said there are times when using your general behavior in the app to influence results could be helpful, so Ramesh said, “We are trying to figure out how to balance those aspects.”
She also noted that her preferences may change depending on the time and context: she can either drop a certain diet or go out to eat without her children. So you can adjust your preferences at any time, or on the contrary, dive more deeply into one of them by selecting a list from the home page.
When asked how this affects Yelp’s advertising business, Ramesh said it won’t influence the ads you initially see, but the ads will come with similar “Because you liked X” messages tied to your preferences.
“I would not be surprised if the advertiser we show will be you according to your preferences [eventually], but there is no ETA in that, “he added.