NOTE: Pitch accessible at https://ugli.tech/pitch.

NOTE: Website video demo accessible at https://ugli.tech/demo.

NOTE: Pitch deck slides accessible at https://ugli.tech/slides.

Did you know that the ugli fruit is also called the uniq fruit? With Ugli, ugly and misshapen produce no longer go to waste. Farmers and restaurants connect to form mutually beneficial transactions.

Inspiration

On average, farmers in the United States alone waste over 20 billion pounds of food annually. Fruits and vegetables that are deemed just a little too ripe, small, or oddly shaped never make it into the hands of supermarkets or national food carriers, and even perfect produce may not leave the farm when local, small-time farmers don’t have a means of accessing nearby clients. Similarly, restaurant owners often face staggeringly high prices for basic ingredients, but in the status quo have little incentive to reach out to suppliers other than national chains. Moreover, restaurant owners don’t require cosmetically perfect ingredients when menu items only reflect the end result of their cooking. To bridge the gap between farmers and restaurant owners alike, we set out to create Ugli.

Through Ugli, we hope to use artificial intelligence, machine learning, and technology in general as a means of transforming careers and improving lives. The fields of agriculture and environmental sustainability have recently become prominent AI verticals, and we hope to revolutionize the process of turning ugly waste into abundant produce.

What it does

Ugli is a web app aimed at revolutionizing the way fresh produce is sold by local farmers. It serves as a link between farmers and local restaurant owners to help farmers sell cosmetically imperfect ingredients or ingredients in high supply at a reduced price to help avoid excessive food waste.

Without Ugli, farmers struggle to sell all of their food—especially imperfect produce—and therefore rely on food carriers or charity organizations to reach out to them. These organizations often fail to cater to individual farmers, resulting in billions of tons of fresh produce going to the landfill each year. That’s why we invented Ugli, an application that allows farmers to reach out to those restaurants and businesses. Not only does this waste contribute to major environmental problems such as air pollution, climate change, and more, but it also strips farmers of a huge portion of the income they need to survive.

First, farmers can view a curated list of nearby restaurants and the ingredients that each restaurant needs. Internally, our code determines the cuisine of a given restaurant and translates that into a list of common ingredients that the restaurant needs along with the likely quantity. Moreover, restaurant owners have the option to upload an image of their menu, and our optical character recognition AI/ML algorithm converts this image into a list of menu items which we then convert into a list of ingredients by calling the Spoonacular API.

In addition, through our automated Twilio SMS system, we make it easy and efficient for farmers to reach out and strike deals with local restaurants.

How we built it

After a few hours of wireframing, brainstorming new features, and assigning tasks, we divided ourselves into 2 frontend, 1 backend, and 1 AI/ML developer and started working. Mason and Howard designed the UI/UX, Tony worked on creating the Cloud Firestore backend and linking it to the Spoonacular recipe API call, and Vignav built the Twilio SMS system after creating and training the AI/ML algorithms for text recognition and menu processing.

Challenges we ran into

Our biggest challenge was getting the Spoonacular API call to process the inputs from our website form. We needed two separate API functionalities and spent a majority of our time refining the dish and ingredient results from Spoonacular. We were able to overcome this problem by looping through the API call twice to access both API search functionalities. Integrating the features with both the text recognition ML algorithm and the Twilio SMS messaging system was also a major challenge as it was new technology we were trying out.

Accomplishments that we're proud of

We're proud of the unique way in which we were able to combine and build off of research from various sources and fuse them into one final product. It was really exciting to see all of our features, from OCR-based menu uploading to Twilio SMS notifications to cuisine-based ingredient generation, come together and for us to successfully transform something that has so far been primarily an untested, theoretical concept into an innovative working product. We're really proud of everyone's dedication to the project and determination to tackle food waste with a revolutionary solution.

What we learned

We entered this hackathon with absolutely no prior knowledge of programmable SMS notifications or restaurant-based ML development and filtering, and after a day of hard work, we completed Ugli. Working with vast amounts of AI/ML training data, mathematical algorithms, and online phone numbers more made this project really fun!

What's next for Ugli

For the second iteration of our Twilio messaging feature, we hope to add an in-app messaging system for farmers to continue negotiating deals and making arrangements with restaurant owners through Ugli's website. In addition, we are in the process of designing and implementing a K-means based clustering algorithm that allows farmers to enter a few of their key ingredients and receive a list of the top 10 restaurants that satisfy criteria such as distance from the farm, ingredient necessity, and more.

Most importantly, Ugli’s solutions to food waste apply to far more than farmer-restaurant relationships. While our work is disruptive in the agricultural sector, our technologies can be applied to various other scenarios, such as food waste by patients in hospitals, effective food donation to homeless shelters, and more.

Pitchfest

Our pitch deck can be found at https://ugli.tech/slides.

Built With

Share this project:

Updates