Monday: FINAL Fall Bootcamp Application Deadline! Apply Now

Made at Metis: Making Predictions - Snowfall in California & Home Prices in Portland

By Emily Wilson • December 18, 2017

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

James Cho
Metis Graduate
Predicting Snowfall from Weather Radar with Gradient Boost

Snowfall in California's Sierra Nevada Mountains means two things - water supply and great skiing. Recent Metis graduate James Cho is interested in both, but chose to focus his final bootcamp project on the former, using weather radar and terrain information to fill in gaps between ground snow sensors.

As Cho explains on his blog, California tracks the depth of its annual snowpack via a network of sensors and occasional manual measurements by snow scientists. But as you can see in the image above, these sensors are often spread apart, leaving wide swaths of snowpack unmeasured.

So, instead of relying on the status quo for snowfall and water supply monitoring, Cho asks: "Can we do better to fill in the gaps between snow sensor placement and the infrequent human measurements? What if we just used NEXRAD weather radar, which has coverage almost everywhere? With machine learning, it may be able to infer snowfall amounts better than physical modeling." 

Read his blog post to learn more about the project, see the results, and find out how he got there. 


Lauren Shareshian
Metis Graduate
Predicting Portland Home Prices

For her final bootcamp project, recent Metis graduate Lauren Shareshian wanted to incorporate all that she'd learned in the bootcamp. By focusing on predicting home prices in Portland, Oregon, she was able to use various web scraping techniques, natural language processing on text, deep learning models on images, and gradient boosting into tackling the problem.

In her blog post about the project, she shared the image above, noting: "These houses have the same square footage, were built the same year, are located on the exact same street. But, one has curb appeal and one clearly does not," she writes. "How would Zillow or Redfin or anyone else trying to predict home prices know this from the home’s written specs alone? They wouldn’t. That’s why one of the features that I wanted to incorporate into my model was an analysis of the front image of the home." 

Lauren used Zillow metadata, natural language processing on realtor descriptions, and a convolutional neural net on home images to predict Portland home sale prices. Read her in-depth post about the ups and downs of the project, the results, and what she learned by doing. 


See more projects created by Metis graduates here

Similar Posts

The Value of an “Unstructured Mathematical Mind” in the World of Startup Data Science

By Emily Wilson • April 07, 2019

“Learn, viciously.” That's the advice Metis graduate Leon Johnson gives to those interested in the bootcamp. And he's no stranger to following his own advice when dedicated to professional and academic pursuits. In this post, read his story, which involves a Math degree, being commissioned into the Air Force, a master's degree, the bootcamp, and his current role as Data Scientist.

How a Former Software Engineer’s Dream of Working in Machine Learning Became a Reality

By Emily Wilson • March 18, 2019

After 20+ years of working as a senior-level software engineer for companies like Goldman Sachs and Bank of America, Emy Parparita was looking for a change. Read how the bootcamp helped him transition to his current role of Machine Learning Engineer at Quora.

Made at Metis: Predicting and Mapping Using Geographic Data

By Emily Wilson • February 14, 2019

Bootcamp graduates Joyce Lee and Matt Maresca covered a lot of ground using geography as a framework to design their final projects. Lee did on a county-by-county analysis to predict mortality rates from overdoses, while Maresca used satellite imagery to map farmland, urban development, and natural resources in Shanghai. Read the post for more!