Inspiration

According to a study, a typical American on average spends around 40 minutes of the day thinking about where to eat. That amounts to 240 hours or 10 days per year. Think about all you can do in that time, you can add a fitness routine, a Netflix show, commute to work, socialise with friends.

Mark Zuckerberg once said "I really want to clear my life to make it so that I have to make as few decisions as possible about anything except how to best serve this community" backing his choice of wardrobe. We wanted to do something similar here for food.

What it does

Munchbot recommends you few options of restaurants and let you choose between them in a fun game based on your personalized profile. It takes into account your budget, dietary restrictions, cuisine preferences and proximity to the restaurants.

After the visit, the customer can update if the liked the restaurant or not and based on that, future options will be tailored

How we built it

We used Ruby as a backend to talk to our messenger API. For the website landing page, we've used React.

Challenges we ran into

As we were new to the messenger platform, it required a lot of trial and run to get the chatbot up and running. Integration of recommendation engine built using python with Ruby messenger app. We initially started implementing the backend with node.js, which was another hurdle. We were not able to fully implement the idea as we faced some technical challenges.

Accomplishments that we're proud of

  • The idea when implemented on a scalable level with actually benefit a lot of customers due to it's utility to save time in the decision making process.
  • We did a lot of research on the UI/UX designs considering the customer requirement analysis in our case and came up with a customer friendly User Interface which requires minimum text input.

What we learned

Messenger platform APIs, Chatbot, Wit.ai

What's next for Munchbot

  • Add poling functionality for a group to vote for a place to go
  • Venmo functionality to split costs
  • Collect training data for better personalization
  • Recommendation engine based on NLP on reviews
  • Personalize experience (Parking preference, Payment preference, Pet preference, Drive thru, Discount deals, Music - Karoke, Live, By appointment/no appointment)
Share this project:
×

Updates