Co-Hosted by NYC Open Data meetup and NYC Data Science Academy meetup.
Presented by NYC Data Science Academy students who just finished the 12-week full time program. Apply April 2017 bootcamp Now.
Can't make to it? Join it online: https://meetings.webex.com/collabs/#/meetings/detail?uuid=MDJOTT7E8RQBLS0BILKN4Y7NES-PVDL&rnd=[masked]
During this event you will see some of the best machine learning and big data projects created by NYC Data Science Academy 12-week Data Science bootcamp students.
You will also have an opportunity to meet our bootcamp students and find out more about what it is like to be a student at NYC Data Science Academy and gain an overview of the program. Join us for data wrangling tips, fun facts and in-depth discussions.
6:30 pm - 7:00 pm Check in, mingle, enjoy food & drinks
7:00 pm - 8:30 pm Student presentation
8:30 pm - 9:00 pm Network and meet our students
Project 1: What Are Those?! Sneaker Brand Classification using Machine Learning
By Regan Yee
There are many ways one can classify shoes - by color, by size, by design, by brand, etc. Sneaker fanatics, commonly known as sneaker-heads, seem to be able to identify shoes by brand and product name very easily. In this project, I attempt to replicate a sneaker-head's expertise by classifying sneaker by brand using KNN and convolution neural networks.
Project 2: Ninkasi: A beer recommendation system
By Luke Chu, Nelson Chen, Xinyuan Wu, & Yuan (Alex) Li
We present Ninkasi, a beer recommendation app for all beer lovers! Whether you want a light, sweet beer or a darker, bitter brew, Ninkasi will certainly recommend the best beer based on your favorite brew.
Ninkasi combined both collaborative filtering and content-based algorithms, thus it is capable of recommending from either ratings or reviews, based on user preference. The recommendation algorithms are incorporated into a meticulously designed web app powered by Python Flask package. This allows users across the US to explore our projects and get beer information and recommendations.
Project 3: Predicting House Sales
By Jason Sippie
The sale of a house is a valuable event for many parties. Real estate brokers, mortgage originators, moving companies – these businesses and more would greatly benefit from being able to get out in front of their competitors in making contact with prospective home sellers. But who are these prospects? The goal of my project is to build out analytics to predict who will soon put their house up for sale using publicly available data.
Project 4: Orpheus: A Multi-User Music Recommendation System
By Joshua Litven, Oamar Gianan, James Lee
In this project we address the challenge of creating a playlist for multiple users with different tastes and preferences and provide a uniformly fantastic listening experience.
Imagine an app where, upon you and your companions logging in to your music devices, aggregates everyone’s listening history and automates a playlist that everyone would enjoy!
We created just an app: Orpheus. With Orpheus, multiple users can login to their Spotify accounts and find songs they can all rock out to. The order of the tracks can be based on mood, tempo and more. Orpheus was developed in Flask, using the Spotify Web API to get user data.
Project 5: The Dendrotrons: Allstate Claim Severity Kaggle Competition
By Anne Christine Valle, Conred Wang, Jason Sippie, Jhonasttan Regalado, Kawtar Belmkaddem, & Nathan Stevens
To predict AllState’s auto insurance severity claims, Team Dendrotrons used supervised ML Models (XGBoost, Neural Net, Linear & Logistic Regression) yielding $1124 MAE close to the winning model with $1118 MAE. Transformation on the anonymized dataset was based on learnings from unsupervised ML models (PCA, SVD, hierarchical clustering)