Topics include recommendation systems,Topic Modeling and Natural Language Processing.
Movie Recommendation System
Built a movie recommendation engine with end-to-end pipeline for personalized top recommended movies and conducted extensive experiments.
Customer Segmentation and Anomaly Detection
Working on a Research paper for bank customer segmentation and anomaly detection based on transaction behavior with innovative work
Text Mining for Seeking Alpha in Stock Market
Developed a prediction system by web crawling and leveraging Yahoo Finance News for stock price prediction; simulated a systematic trading strategy
Topics include data exploration, visualization and distribution system, etc.
NYC Citibike Share Visualization
Analyzed and visualized the COVID-19 pandemic’s impact on New York City residents who use Citibike as part of their commuting tools.
PySpark for PageRank Program
Deployed Spark and HDFS in Google Cloud Dataproc and built a PySpark application to generate a web graph and page rank program from entire Wikipedia