Demystifying Data Science Free Online Conference is July 30-31! Register Now

Made at Metis: Recommendation Systems for Making Meals + Choosing Beer

By Emily Wilson • July 08, 2019

This post features two final projects from recent graduates of our data science bootcamp. Take a look at what's possible to create in just 12 weeks.

Produce2Recipe: What Should I Cook Tonight? 
Jhonsen Djajamuliadi, Metis Bootcamp Grad + Data Science Teaching Assistant

After trying out a couple existing recipe recommendation apps, Jhonsen Djajamuliadi thought to himself, “Wouldn’t it be nice to use my phone to take photos of stuff in my refrigerator, then get personalized recipes from them?”

For his final project at Metis, he decided to go for it, creating a photo-based recipe recommendation app called Produce2Recipe. Of the project, he wrote: Creating a functional product within 3 weeks was not an easy task, as it required some engineering of different datasets. For instance, I had to collect and manage 2 types of datasets (i.e., images and texts), and I had to pre-process them separately. I also had to build an image classifier that is robust enough, to recognize vegetable photos taken using my phone camera. Then, the image classifier had to be fed into a document of recipes (i.e., corpus) which I wanted to apply natural language processing (NLP) to." 

And there was much more to the process, too. Read about it here.


What to Drink Next? A Simple Beer Recommendation System Using Collaborative Filtering
Medford Xie, Metis Bootcamp Graduate

As a self-proclaimed beer enthusiast, Medford Xie routinely found himself looking for new brews to try – but he dreaded the possibility of disappointment once actually experiencing the first sips. This often led to purchase-paralysis. 

"If you ever found yourself staring at a wall of beers at your local supermarket, contemplating for over 10 minutes, scouring the Internet on your phone looking up obscure beer names for reviews, you are not alone...I often spend too much time looking up a particular beer over several websites to find some kind of reassurance that I’m making a good choice," he wrote. 

For his final project at Metis, he set out " to utilize machine learning and readily available data to create a beer recommendation engine that can curate a customized list of recommendations in milliseconds." 

How did he do it? Read more about the project on his blog

__________

See more examples of Metis student projects here


Similar Posts

data science
How to Learn Data Science Quickly and Effectively

By Metis • July 16, 2019

There’s no shortage of discussion in the data science community about WHERE to best learn data science. However, there’s precious little discussion of a topic that’s arguably more important: HOW to learn data science. In this guest post from Dataquest, read about the 3 crucial things you need to do no matter where you're learning.

data science
Made at Metis: Analysis of Bitcoin's Utility + Cultural Impact of Cosmo Covers

By Metis • April 26, 2019

In this edition of the Made at Metis blog series, check out two bootcamp final projects: an analysis of bitcoin's utility and an examination of the cultural impact of Cosmopolitan magazine covers.

data science
Seattle Data Science Career Advice: Landing a Job in The Emerald City

By Marybeth Redmond • April 23, 2019

Let’s face it: today's job market is confusing – perhaps even more so in data science, where job titles are all over the map, needed skill sets aren’t always clear in job descriptions, interviews are famously intense, and so forth. In this post, Metis Seattle Career Advisor Marybeth Redmond explains how to effectively navigate the tricky waters of the job search, particularly in the Seattle area.