top of page
yelpdataset1.png
Explore Yelp Dataset

04/2019

Analyze GB-sized Yelp dataset using PySpark and Spark SQL and perform sentiment analysis on reviews.

food_insepection.png
Food Inspection Failure Detection in Chicago

11/2017 - 12/2017

SmartPect, a product based on predictive analytics to detect food inspection failure in advance for Chicago city.

flightdata.png
Flight Data Wrangling and Visualization

03/2019

Extract and organize flight data using Python, and visualize both tabular and spatial data. 

forwebsite2.jpg
Home Prices Prediction for Boston

09/17 - 11/17

Use OLS regression to build a predictive model for home prices in Boston.

Indicity_CHANGE.jpg
Predicting Urban Growth for Marion County in 2020

04/2018 - 05/2018

Apply a top-down approach to predict the possible urban growth locations for Marion County in 2020 and offer a proposal for locating the suitable future development.

logo.png
Quantify Bike Share Demand in Philadelphia

01/18 - 05/18

A  predictive model to of bike share demand in Philadelphia citywide, together with a cost-benefit analysis tool.

© 2018 by Yayin Cai

bottom of page