Made atMetis

Josh peng
made at metis
Data Sciencing Motorcycles: Lean Assist

Josh Peng

Motorcycle Lean Assist uses a convolutional neural network to detect the lean angle of a motorcycle through image classification, providing you with rider feedback on your current lean angle so you don’t have to guess.

Tim martin
made at metis
Promoting Positive Climate Change Conversations via Twitter

Tim Martin

Tim's project explores the conversations about climate change that took place on Twitter in March 2017. With 1 million tweets from 560,000 users, Tim identified people belonging to different communities and used tools such as the Twitter API, Spark, NetworkX, and Gephi to derive insight from those conversations.

Max melnick
made at metis
Improving Brand Analytics with Image Logo Detection

Max Melnick

Using a convolutional neural net in TensorFlow, Max developed an application that can improve brand analytics through logo detection in images.

Naoya kanai
made at metis
Music Composition with LSTMs

Naoya Kanai

Naoya explores the intersection between data and art by designing a recurrent neural network utilizing Long Short-Term Memory nodes (LSTMs) to learn patterns in the Six Cello Suites by J.S. Bach and generate its own musical fragments.

Will chernetsky
made at metis
Creating a Beer Recommendation Engine

Will Chernetsky

To combat flaws in other reccomendation systems, Will decided to use natural language processing of beer reviews to find similarity of language used to describe beers. He found the words people use to describe beer give better results than arbitrary scores or styles.

Peter rasmussen
made at metis
Marijuana through the lens of the New York Times

Peter Rasmussen

The legality of and public’s view towards marijuana is rapidly changing as more states decriminalize and legalize the drug. As such, how have the words associated with marijuana in news articles changed over time?

Justin chien
made at metis
Identifying cars using Motordex

Justin Chien

Using Flask, Justin created a web app to combine his passion for photos and cars. Motordex uses the decision tree process and different models to identify cars based on a submitted picture.

Hasan haq
made at metis
Cracking Passwords with Neural Networks

Hasan Haq

You don't have to be an expert to know that password security is a big issue for companies these days. It seems every other week you hear of a well known website getting hacked. Hasan Haq's project uses neural networks to generate "dictionary" word lists to be used in password cracking.

Katherine pully
made at metis
Take Control of your Healthcare with MedTracker

Katherine Pully

MedTracker i s a system to track your (psychiatric) medications and your moods and to compare what is working well for other users. Users can register as a patient or a doctor.

Brianholligan
made at metis
Using convolutional neural networks to predict clothing

Brian Holligan

The Clothing Predictor is a web app that uses convolutional neural networks to identify images with one person in them, and then predict the clothing being worn by that person.

Lizhang
made at metis
Personalizing Travel Recommendations with MemoTrek

Li Zhang

MemoTrek is an application that takes your travel photos as input and makes personalized recommendations for future travel destinations. It provides two types of recommendations: you-may-also-likes for a similar type of experience and something-different for new adventures.

Rohanshah
made at metis
Parking Lot Image Classification through OpenCV and a Flask App

Rohan Shah

As more data is sourced through satellite imagery it has become an important task to accurately identify important hotspots and targets within these images so as to classify them for practical use.

Emilybarry
made at metis
Applying Data Science to the Supreme Court

Emily Barry, Data Scientist at LegalServer

The Supreme Court is arguably the most important branch of government for guiding our future, but it's incredibly difficult for the average American to get a grasp of what's happening.

Micheallai
made at metis
Basketball Player Tracker

Micheal Lai, Strategy Consultant & Data Scientist at IBM

Micheal created a system that can track players in a basketball clip and translate them to a coordinate grid. This kind of motion tracking already exists in the form of SportVU - but you can use the accessibility of YouTube clips to create player tracking.

Emilyschuch
made at metis
Halting the Spread of HIV

Emily Schuch, Data Scientist at Assembly Media

The HIV incidence rate is defined as the number of new HIV infections in a population in a given year. A rate of 0.4% means that 4 out of every 1000 people became newly infected with HIV.

Briankim
made at metis
Politweets

Brian Kim, Data Scientist at FabFitFun

The app tracks twitter trends in volume, sentiment, and topicality for 2016 Election candidates. It was done using Flask, MongoDB, D3, Vader Sentiment Analysis, and Gensim on an EC2 Server.

Ruichang
made at metis
Estimating House Prices in San Francisco

Rui Chang, Lead Data Scientist at Target

This project is trying to estimate house prices based on the features using publicly available data, and build a web application for house prices estimation.

Kenmeyers
made at metis
KenKen Solver

Ken Myers, Jr. Data Scientist at Uncommon Goods

Ken uses computer vision to solve KenKen puzzles. (Currently this application only accepts 4x4 KenKens). Simply upload a puzzle and get the solution.

Davidepuis
made at metis
A statistical analysis of minesweeper – Placing the Mines

David Dupuis, Data Scientist Researcher at Kwanko

There are some key elements to coding the game that can and probably should be memorized as they have other practical applications in computer science.

Jeffwen
made at metis
Visaurant: Reimagining the food search experience

Jeff Wen, Data Scientist at Tesla

Visaurant is a reimagination of the way users search through images that they are interested in. One prime use case for Visaurant is in sorting and filtering through food images (hence VIS -ual rest- AURANT).

Jamief
made at metis
The (Data) Science of Binge Watching on Netflix

Jamie Fradkin, BuzzFeed, Jr. Data Scientist

Who among us hasn’t fallen victim to the addictive power of a binge-worthy Netflix show? For Jamie's final project at Metis, she chose to explore elements in popular shows that might lead you to start “binge watching” on Netflix.

Ash
made at metis
Investigating Worker Exploitation in California

Ash Chakraborty, Data Scientist at Credit Sesame

At a recent DataKind SF event, Ash was rather intrigued by the challenges faced in investigating wage theft and other labor violations not just throughout the nation, but also specific to California and the Bay Area regions.

Frederikdurant
made at metis
End-to-End Funding Loan Predictor

Frederik Durant, Staff Member Data Innovation at Colruyt Group

Frederik delved deep in the micro-finance mechanics at Kiva, looking for a practical problem to solve.

Yongcho
made at metis
NBA Matchup Analysis

Yong Cho, Data Scientist at GrubHub

Yong built an analytics tool for Vantage sports.

Henridwyer
made at metis
Chord Classification using Neural Networks

Henri Dwyer, Data Scientist at Dataiku

Henri is currently working on classifying chords from audio using neural networks.

Ryanlambert
made at metis
PUBmatch.co

Ryan Lambert, Data Scientist at Gild

PUBmatch.co makes it easier to parse through the giant open access database PubMed by allowing you to input anything from a news article clipping to an email thread.

Garretthoffman
made at metis
The Science of Singing Along

Garrett Hoffman, Senior Data Scientist at StockTwits

Garrett's project explores the "physics of pop culture", analyzing the culture that we love to consume every day with data science.

Andregatorano
made at metis
Numer.ai and Ensembles - Voting, Averaging, Rank Averaging

Andre Gatorano, Data Scientist at Blitsy

In the spirit of the Kaggle revolution, an industrious and risk taking hedge fund put their investments in the hands of the public.