This project aims to analyze the impact of the COVID-19 pandemic on Airbnb bookings in Chicago and Boston using robust data modeling techniques. It explores changes in traveler preferences, occupancy rates, and revenue, providing insights for stakeholders.
- Project Overview
- Problem Statement
- Project Objective
- Data Analysis
- Business Insights & Recommendations
- Future Scope
This project, hosted by the Scrum Sprinters team, focuses on analyzing the impact of COVID-19 on Airbnb bookings in Chicago and Boston. The study employs advanced data science techniques and project management tools to understand and address real-time challenges experienced by all stakeholders in a platform-based business model.
The COVID-19 pandemic has exerted profound impacts on urban centers globally. This study seeks to uncover and analyze the comprehensive impact of the COVID-19 pandemic on Boston and Chicago, focusing on key areas such as public health outcomes, economic disruptions, recovery efforts, and changes in urban mobility.
Utilize given datasets on Airbnb to solve real-time problems using robust modeling techniques.
- Chicago: Sharp increase in nightly rates coinciding with a decrease in COVID-19 cases.
- Boston: Similar trends indicating a recovery in the travel and accommodations sector as cases decline.
- Data Set Description: Provided a detailed overview of the datasets used, identifying trends and patterns in the raw data.
- Handling Highly Correlated Features and Outliers: Conducted correlation checks and outlier detection to improve data quality and reliability.
- Handling Missing Values: Used techniques such as Gradient Boosting for imputing missing values, enhancing the dataset's completeness and reliability.
- Multicollinearity Check: Identified and removed highly correlated features to improve model performance.
- Predictive Models: Employed XGBoost for data modeling to identify feature importance.
- Difference in Differences Analysis: Assessed the impact of COVID-19 on Airbnb with metrics for Boston and Chicago.
- Data-Driven Approach: Emphasis on robust data modeling to understand Airbnb’s response to the pandemic.
- Adaptive Methodologies: Use of agile practices like scrums and sprints for timely delivery.
- Risk Management: Early identification and management of high-risk tasks.
- Collaborative Estimation: Team collaboration in effort estimation and consensus-building.
- Quality Control: Addressing multicollinearity and outliers for reliable data modeling.
- Change Management: Strategies for hosts and stakeholders highlighting adaptability.
- Longitudinal Study: Track changes over a longer period to capture post-pandemic recovery phases.
- Competitive Analysis: Compare Airbnb's performance with other platforms.
- Expand Geographic Analysis: Include more cities or countries for global comparison.
- User Behavior Analysis: Focus on changing consumer preferences towards remote work and longer stays.
- Technology Integration: Explore emerging technologies like AI and blockchain to enhance project management processes.