Seattle Airbnb Data - Data Analysis
Libraries used : Numpy, Pandas, SciKit learn, Matplotlib, Seaborn
Motivation : Renting or finding accomodation is one the most common problems faced while travelling. This project is a beginner level approach to analyse the main factors determining the pricing of accomadations, based on property types and their amenities. This will give an insight into efficiently setting cost, thereby saving money, and getting better review scores.
Files in Repository : Listings.csv from Seattle Airbnb Dataset, my.ipynb, and 3 graphs.
Summary of Analysis : Average prices of Condominium property types are the highest and they gradually decrease from Houses and Lofts to Apartments and other types. Pricing is mainly influenced by number of bedrooms,bathrooms and number of amenities. Random Forest Regression is used to predict prices of unknown property types based on the important features concluded from the correlations heatmap.
Acknowledgements : I have refered the following kaggle notebooks for my project: https://www.kaggle.com/kaushikjag/airbnb-seattle-new-host-pricing-tip-prediction and https://www.kaggle.com/aleksandradeis/airbnb-seattle-reservation-prices-analysis