COCKTAIL MATCH

• 

  Color selection: what color do you like?

• 

  Flavor selection: What flavor do you like?

• 

  Season selection: What is the season like?

• 

  Main spirit selection: What main spirit so you like?

• 

  Occasion selection: Any occasions?

• 

  Final result page

Inspiration

• Wisconsin is Home to Some of the Drunkest Cities in the US, we are intrigued by the cocktail scene.
• We noticed a lack of detailed cocktail descriptions, making it difficult to decide what to order.
• This sparked the idea of creating a system to recommend cocktails based on individual preferences.

What it does

• COCKTAIL MATCH recommends cocktails based on user preferences.

How we built it

• We crawled data, cleaned it, visualized it, and then used cosine similarity to build the recommendation system.

Challenges we ran into

• Crawling data posed a significant challenge due to its complexity.

Accomplishments that we're proud of

• Completing the project in a short amount of time.

What we learned

• We gained valuable experience in data crawling, cleaning, visualization, and building recommendation systems.

What's next for COCKTAIL MATCH

• We aim to further refine the recommendation system and explore additional features to enhance user experience.

Built With

• css
• flask
• html
• javascript
• python
• r
• sklearn
• tableu
• tdidf