Airbnb: New User Bookings
Predicted in which country a new user will make his or her first booking
Introduction
New users on Airbnb can book a place to stay in 34,000+ cities across 190+ countries. By accurately predicting where a new user will book their first travel experience, Airbnb can share more personalized content with their community, decrease the average time to first booking, and better forecast demand.
Summary
Airbnb project involved processing 200,00 consumer behavior data to predict Airbnb new users' bookings. As the leader of my team, I was in charge of the Decision-Tree analysis using R and assisting members with Logistic Regression analysis. Even though our project only required data analysis, I proposed to use "ggplot2" to visualize our data in an interactive way. Consequently, we not only successfully identified the significant vairable but also created a fun presentation to impress classmates.
Furthermore, we improved test data prediction from 20% to 87% accuarcy, a mere 1.6% discrepancy from the highest accuracy recorded in Kaggle Data Science Competition. To me, this experience validated my public-speaking ability and the capability of data analysis.