BOYO: Your
Real-World
Hospitality &
Booking
Data Playground
BOYO is a ready-to-use synthetic dataset that mimics the experience of a digital hospitality platform. Ideal for price optimization, guest segmentation, cancellation prediction, and occupancy forecasting.
Overview
BOYO is a synthetic dataset that brings the experience of a digital hospitality platform to life. From discovering a property to booking, checking in, and leaving reviews, it mimics the full journey of a guest. It's a great resource for anyone looking to explore how people interact with stays, uncover booking trends, or test systems behind platforms like Airbnb or Booking.com.
Whether you're a developer, analyst, or data science enthusiast, BOYO is packed with realistic mock data — users, properties, pricing, reviews, bookings, and more. It's ideal for building personalized stay recommendations, predicting cancellations, analyzing occupancy rates, or testing booking logic and payment flows. With this dataset, you can experiment, learn, and build confidently in the world of digital lodging.
Full Hospitality Lifecycle
Simulates a complete hospitality platform experience including property listings, room bookings, customer profiles, host management, and reviews.
Built for Development & Testing
Excellent for building and testing price optimization engines, guest segmentation models, churn prediction systems, and availability forecasting pipelines.
Backend Feature Testing
Useful for developers working on availability checks, pricing engines, booking pipelines, and payment processing systems.
Rich Transactional Data
Includes transactional data for bookings, cancellations, payments, discounts, and loyalty systems. Supports location-based analytics and seasonal trend tracking.
Analytics & Research
Structured for SQL practice, data cleaning exercises, dashboard creation, performance benchmarking by region or property type, and real-world data modeling.
How it Works
AI-Generated & Fully Synthetic
The Boyo dataset was synthetically generated to replicate the user experience of an online accommodation and room-booking platform. Advanced AI agents were used to model realistic behaviors of both travelers and accommodation providers — with zero real hotel or guest data.
Realistic Simulation with Privacy
It simulates hotel listings, room availability, bookings, user reviews, pricing, and location-based search — without any real transactions or guest data, ensuring ethical use across all hospitality applications.
High-Quality & Safe for Use
Built for testing hospitality booking engines, analytics dashboards, and customer-facing travel apps — 100% privacy-compliant and ready to use out of the box.
Dataset Schema
A comprehensive relational model representing a modern hospitality booking platform engineered for deep analysis and complex querying.
Users
Contains user data like login details, contact info, and role (customer, host, admin), linked to bookings, payments, and reviews.
Properties
Represents properties listed by hosts, including address, description, and host association, linked to rooms and promotions.
Rooms
Stores room info within properties, including type, price, capacity, and amenities.
Bookings
Tracks room bookings, including check-in/check-out dates, total amount, and booking status, associated with users and rooms.
Payments
Records payments for bookings, including method, status, and transaction details.
Reviews
Allows users to leave reviews for properties, including ratings and comments.
Facilities
Details amenities available at properties, such as gyms or pools, linked to specific properties.
Property Images
Stores images related to properties, including interior, exterior, and room photos.
Promotions
Stores promotional codes and discounts for properties, defining discount percentage and valid dates.
Property Promotions
Links properties with promotions, allowing hosts to apply discounts for a limited time.
Notifications
Tracks notifications sent to users, such as booking updates or promotional alerts, with message content and read status.
- CSV
- JSON
- Excel
- MySQL
- PostgreSQL
- SQL Server
- Snowflake