Booked-blocked Classifier for Booking Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems cannot accurately differentiate between genuine bookings and unavailability caused by other reasons on merchant websites, such as seasonal closures or owner occupancy, leading to unclear insights into travel trends and economic activity.
Innovation Solution
A method and system that compares web content from merchant websites at different times to identify apparent bookings, using additional information about the merchant, geographical area, and other similar merchants to determine whether unavailability is due to genuine bookings or other factors, and stores genuine bookings in a database for analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If calendar unavailability is used to indicate bookings, then availability information is provided to viewers, but it is impossible to determine whether unavailability is due to genuine bookings or other reasons such as seasonal closures or owner occupancy
Solution Approach 1:
A machine learning model acts as an intermediary between the calendar unavailability data and the booking determination. The model analyzes additional content from merchant websites (such as property descriptions, location information, and seasonal patterns) to classify whether unavailability represents a genuine booking or a blocking event like seasonal closure or owner occupancy.
Solution Approach 2:
The system changes the parameters used to determine booking status by incorporating multiple features beyond simple calendar unavailability. These features include text content analysis, seasonal patterns, property type, and location data, transforming the classification from a binary available/unavailable state to a nuanced booking/non-booking determination.
2Measurement precision
If web content comparison is performed to identify apparent bookings, then booking detection capability is improved, but device complexity and processing requirements increase
Solution Approach 1:
The system performs self-service by automatically crawling and analyzing merchant website content without requiring manual intervention. The machine learning model autonomously processes web content, extracts relevant features, and classifies booking status, reducing the need for complex manual verification systems.
Solution Approach 2:
The patent replaces manual booking verification mechanisms with automated web crawling and machine learning classification. Instead of human analysts examining calendar data, an automated system uses natural language processing and pattern recognition to determine genuine bookings, significantly reducing operational complexity.
3Productivity
If calendar data is collected at regular intervals, then real-time booking insights are provided, but loss of time for data collection and processing occurs
Solution Approach 1:
The system performs preliminary actions by pre-processing and analyzing web content as it is collected, rather than batch-processing later. The machine learning model is trained in advance on historical data and can immediately classify new booking data as it becomes available, reducing overall processing time.
Solution Approach 2:
The system maintains continuous operation by constantly crawling merchant websites and processing booking data in real-time. Rather than periodic batch processing, the automated system continuously collects, analyzes, and classifies booking information, eliminating idle time between data collection cycles.
Data Source
AI summary
Provided are a system and method for determining whether an apparent booking is a genuine booking or is a blocked period of unavailability that is not the result of a genuine booking. Bookings occur in all sorts of industries, such as travel, medical, entertainment, weddings, catering, and the like. In some examples, the method may include receiving content from a website that includes a listing for an object, identifying a period of unavailability of the object based on the content received from the website, predicting, via a machine learning model, whether the period of unavailability of the object is a blocked period that is not a result of a reservation of the object, the predicting being performed based on additional content visible on the website being input into the machine learning model, and storing an identifier of the period of unavailability and information about the prediction within a storage device.