Hunch: A Cure for Indecision?
A new site provides answers to life, the universe, and just about everything.
Lately, search engines have started focusing more on providing answers to specific questions. Put “capital of Botswana,” for example, into most search engines, and they’ll happily produce both the correct answer and links to relevant sites. But most search engines are of little use with more abstract queries, such as “Which book should I read?” or “What should I make for dinner?”
Hunch, a website that launches to the public today, hopes to be the answer to these questions and many more besides.
Hunch begins “where a search engine leaves off,” according to cofounder Caterina Fake, who previously cofounded the photo-sharing site Flickr and later worked on Yahoo Answers. Fake points out that a normal search engine would provide a user interested in buying a digital camera with links to hundreds of sites that review and compare the latest models. The user then has to sort through that information and figure out which camera is right for her.
In contrast, Hunch asks a few simple, multiple-choice questions, including “What type of photography are you interested in?,” “Do you want a ‘point and shoot,’ an SLR, or a Rangefinder camera?,” and “How much zoom do you want?” before recommending a specific model.
The site offers personalized recommendations for all manner of queries. Although many of the questions already on the site are lighthearted, there’s serious computer science under the hood.
After a user creates an account and logs in to Hunch, she has the opportunity to answer all manner of questions in a box labeled “Teach Hunch About You.” As the user runs through these questions, Hunch builds up reams of data to help with the recommendations that it makes.
In order to fine-tune its recommendations, Hunch balances a user’s responses to questions with information from her profile. Users can indicate whether Hunch’s recommendations were good or not, and this information will help adjust the factors that guide the site’s algorithms in the future.
Fake believes that many existing recommendation systems, such as those used by Amazon or Netflix, struggle because the data that they collect relates to a narrow range of topics. She thinks the problem is that they only have users’ book or movie ratings to work with. “Whether you like Napoleon Dynamite could have something to do with whether you played a lot of pinball as a child,” Fake says.
Fake sees Hunch as a grand experiment, but its success will depend on users’ willingness to generate new content for the site and provide feedback to train its algorithms. Although the company seeded the site with some survey questions and topics, most of what’s there now was added by users themselves during beta testing, Fake says.
In addition to rating whether a result was useful, users can suggest other recommendations or improvements to surveys. New query topics can be added to a “workshop” area to be developed until users’ votes indicate that they are accurate enough to be released as questions on the wider site.
John Riedl, a professor of computer science at the University of Minnesota, who studies recommendation systems and online collaboration, says that Hunch is tackling a fascinating problem, and one that academic researchers have been working on for a long time. Computers are great for creating games like 20 Questions, he says; Hunch, however, is dealing with much more amorphous problems. A single question might have dozens of possible results, and the information that a user provides may not help a computer distinguish clearly among the options.
A key issue, Riedl says, will be whether the site can build up a base of volunteers who are willing to contribute. While projects that rely on user-generated content–such as Wikipedia–represent “some of the extraordinary accomplishments of our time,” Riedl says, Hunch is asking a lot of its users.
Hunch has yet to answer the question of how it could make money, but Fake says that revenue will likely come from sponsored links that appear alongside results. Or if Hunch suggests a particular brand of laptop, the site might get a referral fee if the user goes ahead and buys the device. However, Fake stresses that advertising would only appear after a result is generated and wouldn’t influence the products that the site suggests.
As the site improves, Fake hopes that the results will feel increasingly intuitive, appropriate, and even a little mysterious. She says, “I want it to feel like the Magic 8 Ball experience.”
Keep up with the latest in machine learning at EmTech MIT.
Discover where tech, business, and culture converge.
September 11-14, 2018
MIT Media Lab