Vintnar Recommendation System

Inspiration

Our love of chemistry and how it affects the food and drink we consume every day.

What it does

Vintner provides scientifically backed recommendations for wine. Utilizing a knn algorithm and SingleStoreDB it fetches wines from the database after a user fills out a questionnaire.

How we built it

Vintner was built by

Challenges we ran into

Some challenges we ran into included the planning stage of our project and deciding on what we wanted to do with the given data and how we could implement a productive and useful output.

Accomplishments that we're proud of

We were able to generate a working recommendation system and implement high performing models such as a recurrent neural network and kNN using tensorflow frameworks. We were able to research a large amount of information and apply our new knowledge to the project, as well as learn and develop our skills as data scientists.

What we learned

We learned a lot from this project, the biggest being what we are capable of. Before starting none of us had built a recommender system, a web app, or utilized a cloud based database. Thus, it was very satisfying to work and learn so much from this project!

What's next for Vintnar Recommendation System

What we would love to do is find ways to use different data to improve our recommendations as well as further utilize Single Store to its full capabilities.