Query-Time Attribution Channel Modeling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional attribution systems are inflexible and inefficient, as they require preconfiguration for specific attribution models and marketing channels, making it difficult to adapt to changing user requests and apply different models without significant reconfiguration and resource usage.
Innovation Solution
A query-time attribution system that stores raw data in a database with multiple nodes, each corresponding to a user, allowing for real-time processing and generation of digital attribution reports based on user-specified distribution channels and models, enabling flexible and efficient application of attribution models at query time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If conventional systems preconfigure databases for specific attribution models and marketing channels, then data collection and processing become streamlined for predetermined models, but the system loses flexibility to apply different attribution models or analyze other marketing channels
Solution Approach 1:
The system segments data storage by organizing raw touchpoint data into separate tables or partitions for different marketing channels and attribution models. This allows the database to be structured in a way that supports multiple attribution models without preconfiguration, enabling flexible querying while maintaining processing efficiency through organized data structures.
Solution Approach 2:
The system creates a universal database structure that can serve multiple attribution models and marketing channel analyses simultaneously. By storing raw touchpoint data in a standardized format that can be interpreted by different attribution models, the system eliminates the need for separate preconfigured databases for each model, achieving both efficiency and versatility.
2Speed
If conventional systems pre-process and store data for predetermined attribution models, then queries for those models can be answered quickly, but additional computing resources and processing time are required to reconfigure the database when new models are needed
Solution Approach 1:
The system performs preliminary action by collecting and storing raw touchpoint data in advance in a standardized format, but without pre-processing it for specific attribution models. This allows the data to be ready for immediate querying with any attribution model, eliminating the need for time-consuming reconfiguration when new models are required while maintaining fast query response speeds.
Solution Approach 2:
The system implements dynamic querying capabilities where the same raw data structure can be interpreted and processed by different attribution models on demand. This dynamic approach allows the system to adapt to new attribution models without physical reconfiguration, reducing computing resource consumption while maintaining query speed through efficient data retrieval and processing algorithms.
3Productivity
If conventional systems store touchpoint data for specific marketing channels and attribution models, then the system can efficiently analyze those specific combinations, but it cannot apply attribution models to other marketing channels without additional data collection and processing
Solution Approach 1:
The system stores touchpoint data in a universal, standardized format that can be used for analyzing any marketing channel and applying any attribution model. This universal data structure eliminates the need for separate data collection and processing systems for different channels, enabling efficient analysis of new marketing channels while maintaining high productivity through standardized processing procedures.
Solution Approach 2:
The system uses parameter changes by maintaining a standardized data collection framework that can be reinterpreted with different parameters for various marketing channels and attribution models. By changing the analysis parameters rather than collecting new data, the system can efficiently analyze new channels without additional data gathering overhead, maintaining both productivity and adaptability.
Data Source
AI summary
The present disclosure relates to performing attribution channel modeling in real time using touchpoint data that corresponds to a user-specified set of channels and is retrieved from a database using a user-specified attribution model. For example, in one or more embodiments, a system stores raw data in an attribution database that comprises an aggregator and a plurality of nodes. In particular, each node stores touchpoint data associated with a different user. Upon receiving a query, the system can, in real time, retrieve subsets of the touchpoint data that corresponds to a user-defined set of distribution channels in accordance with a user-specified attribution model. The system then combines the subsets of touchpoint data using the aggregator and generates the digital attribution report using the combined data.