LUB works in entertainment, helping people discover restaurants that match their own taste, beyond the venues that crowded review platforms keep highlighting.
With LUB's CEO, Wildstream implemented clustering and similarity analysis that recommends restaurants visited by people with comparable preferences.
Users discover unique dining experiences outside traditional review rankings, instead of seeing the same popular venues again
Clustering groups users with similar preferences, so recommendations come from people who choose places the same way
Recommendations are based on where comparable groups actually go, not on crowded review platforms that favor volume
Review platforms keep promoting the same popular venues, so users rarely discover new places that fit their taste. People searching for restaurants often rely on these crowded platforms because they have few alternatives. Smaller places that would suit a person's taste rarely make it onto those lists.
Users discover unique dining experiences outside traditional review rankings, instead of seeing the same popular venues again.
Clustering groups users with similar preferences, so recommendations come from people who choose places the same way.
Recommendations are based on where comparable groups actually go, not on crowded review platforms that favor volume.
Sponsored by LUB's CEO, Wildstream implemented clustering and similarity analysis that identifies users with similar preferences. The system recommends restaurants visited by comparable groups, so each user sees places chosen by people with a similar taste profile.
Users are grouped by the restaurants they choose, revealing taste communities that star ratings alone would never show.
Each user is compared with others to find the groups whose preferences are closest to their own taste in restaurants.
Suggestions come from restaurants that comparable groups actually visited, rather than from review counts or popularity.
Independent and lesser-known restaurants reach diners who are likely to enjoy them, not only the venues with most reviews.
Suggestions based on people with similar taste feel more personal and relevant than generic top lists on review sites.
Fresh, well-matched restaurant suggestions give users a good reason to come back every time they plan to eat out.