It’s excellent fun and frequently very tasty to eat out at different restaurants from time to time. The problem lies in figuring out exactly which restaurants are worth the time and which need avoiding at all costs. While the App Store loves to offer plenty of recommendation apps, Ness is the newest out there for restaurant recommendations and it’s looking pretty good, indeed.
Unlike other apps, Ness learns about the user’s tastes by getting them to rate their dining experiences at 10 restaurants they’ve visited. Using such data, Ness then determines what kind of things the user enjoys about dining out, then uses that information to recommend other establishments. The more places that the user rates, the more Ness learns and in turn the more accurate the predictions become.
There’s a social element to the app too with recommendations all connected to similarities between people as well as the user’s friends and their preferences. For those who admit that some friends haven’t got the same taste as them, there’s the option to filter them out so they don’t affect the recommendations from within Ness. All this is conducted via Facebook and Foursquare friends so there’s no need to sign up to yet another social network just for the purposes of this app.
A Likeness Engine gives each restaurant a Likeness score out of 100 with filtering options abound throughout. Users can choose to hide places they’ve already rated for instance, ensuring there’s always a new experience around the corner. No big chains can be switched off too thus meaning the little guys get noticed more so.
Ness‘s developers, the appropriately named Ness Computing, don’t plan to stop with food either with future releases promising recommendations for music, shopping, nightlife and entertainment. Eventually, Ness could arrange the ideal night out all from this one simple yet useful app.
It’s out now and it’s a free app. Give it a shot and do report back on how it goes!
Released: 2011-08-18 :: Category:
Tagged with: Dining Out, free, Lifestyle, Ness, Ness Computing, Personalization, Recommendation, restaurants