Query Token Match Type Selection Using Performance Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems for determining match types in online advertising auctions lack efficiency in selecting the most effective match type based on past performance, leading to potential irrelevance of content to user queries.
Innovation Solution
A process that involves receiving a query token, consulting a database for past performance data on different match types (exact, phrase, and broad), comparing performance differences to thresholds, and selecting the match type that provides the best balance between relevance and coverage, using metrics like click-through rate and cost-per-click.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated match type selection is implemented, then productivity is improved, but device complexity increases
Solution Approach 1:
The system pre-calculates and stores performance metrics for different match types in a database before actual query processing. This preliminary action allows the automated selection process to quickly retrieve and compare pre-computed data, improving efficiency while keeping the real-time processing simple
Solution Approach 2:
A database acts as an intermediary layer between the query processing system and the match type selection logic. The database stores performance information and facilitates automated decision-making without requiring complex real-time calculations, thus improving productivity while managing system complexity
2Reliability
If performance-based match type selection is used, then content relevance is improved, but loss of information increases
Solution Approach 1:
The system extracts only the essential performance metrics (click-through rate, cost-per-click, cost-per-acquisition) from the complete set of possible query data. By selecting only the most relevant performance indicators, the system improves content relevance while minimizing the amount of data that needs to be collected and stored
Data Source
AI summary
Example processes for determining a match type include: receiving a query token from a content provider; consulting a database stored in memory to determine past performance of the query token for associated content, where the past performance includes performance information indicating how well the query token performed for different match types, where a match type indicates a way that components of the query token match components of another query token in order to achieve a token match; determining, based on the performance information, differences in performance between ones of the different match types; comparing the differences in performance to a threshold; and selecting a match type for the query token based on the comparing.