Portfolio

Machine Learning Predictions

On-street Parking Demand Prediction in San Francisco

This project focuses on prediction of on-street parking demand in different time of a day, and day of a week in different locations (represented by fishnet grids here). The prediction results can contribute to the pricing procedure of on-street parking to prevent overuse of parking resources.

Pavement Condition Prediction for the City of El Paso, TX

In this project, our group dive deep into road pavement studies, build Random Forest model to predict pavement conditions for 24000+ road segments in the City of El Paso, TX, and collaborate with El Paso Capital Improvement Department to help them better allocate funding and resources.

Worldwide Population Aging and Birth Rate Prediction

There are two main parts in this project, the first part focus on aging level prediction with multiple features extracted from the Health, Nutrition, and Population Statistics dataset and the second part focus on time series prediction for birth rate in 20 years.

House Price Prediction in Boulder County, CO

In this project, house price prediction for Zillow is carried out with multi-resource commercial and socio-economic data. Feature engineering is an important part of the project, which helps achieve a satifying accuracy and generalizability.

Theft Prediction in Chicago

Theft risk is a function of exposure to a series of geospatial risk and protective factors, such as blight or recreation centers, respectively. The assumption is that as exposure to risk factors increases, so does theft risk.

This project focuses on bike share prediction in Philadelphia, and time factor is explicitly taken into consideration. The model takes advantage of temporal correlation, or serial correlation to achieve better prediction.

Building Height Regression in San Francisco Bay Area

This project combines a series of raster features from GEE (Google Earth Engine) and vector features processed in ArcGIS to predict the building height in San Francisco Bay Area. Visualizations and 3D mappings are carried out.

Web Application Design and Development

Pavement Repairment Prioritization APP for the City of El Paso, TX

This app serves to assist the El Paso Capital Improvement Department in prioritizing road repair projects by overlaying Pavement Conditions Index (PCI) scores on different layers of interest.

San Francisco Parking APP

To give a better sense of on-street parking demands to the public and guide the drivers to nearest off-street parking sites, I carry out this web APP with two main parts, an on-street parking dashboard and a off-street parking map with interactive functions.

Web-based Dashboards and Reports

Neighborhood Livability Evaluation in Chicago

Evaluation of the safety and convenience of each neighborhood in Chicago based on crime data and local amenities.

National Parks Guide for Travelers

Aiming to give recommendations of the national parks in the US, especially for the Christmas holiday, 2021.

Sentiment Analysis on Yelp Reviews in Pittsburgh

Exploration on Yelp restaurant reviews and the relationship between Yelp stars the polarity and subjectivity of comments in Pittsburgh, PA.

Page template forked from evanca