Insight Routing System Using Merchant Bid Propensity
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for distributing customer insights to associated entities often result in excessive data distribution, compromising consumer comfort and utility, as they fail to target entities with whom the customer is likely to interact again, leading to inefficient use of information.
Innovation Solution
A system and method where merchants can bid on receiving insights about consumers based on their propensity to transact again, with the winning merchant identified by a combination of bid amount and transaction history, ensuring insights are shared only with entities likely to benefit, and only when the consumer is likely to transact soon.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If customer insights are broadly distributed to all associated entities, then entities can learn more about customers to earn repeat business and find new customers, but customers become uncomfortable due to excessive data distribution and entities may find little use for the data
Solution Approach 1:
The patent applies local quality by differentiating the distribution of customer insights based on the specific relationship between each entity and the customer. Instead of uniform broad distribution, the system evaluates individual entity-customer pairs and distributes insights selectively to those with high propensity for continued interaction, thereby maintaining consumer comfort while preserving valuable information for relevant entities
Solution Approach 2:
The patent changes the parameter of insight distribution from a static broad-access model to a dynamic model based on calculated propensity scores. The system continuously updates the propensity for continued interaction based on transaction history and other factors, adjusting which entities receive insights accordingly. This parameter-based approach resolves the contradiction by making distribution selective rather than universal
2Productivity
If customer insights are distributed to all entities that have transacted with a customer, then entities can potentially earn repeat business, but the distribution becomes too wide for customer comfort and includes entities with little to no use for the data
Solution Approach 1:
The patent extracts only the necessary portion of customer insights and distributes them to a selective subset of entities rather than distributing all insights to all entities. By calculating propensity for continued interaction, the system identifies and extracts the specific insights that are most likely to lead to repeat business, distributing only those to the most relevant entities, thereby reducing the quantity of recipients while maintaining productivity
Solution Approach 2:
The patent performs preliminary evaluation of entity-customer relationships before distributing insights. The system calculates the propensity for continued interaction in advance based on transaction history and other factors, pre-identifying which entities are most likely to benefit from the insights. This preliminary action ensures that insights are distributed only to entities with high potential for repeat business, optimizing both productivity and reducing the number of recipients
3Reliability
If insights are distributed to entities with high propensity for continued interaction, then consumer comfort is maintained and data utility is improved, but the system requires complex automated evaluation on large scales
Solution Approach 1:
The patent implements self-service by enabling the system to automatically evaluate entity-customer relationships and determine insight distribution without manual intervention. The propensity calculation engine autonomously analyzes transaction history and other data to identify high-value entity-customer pairs, making the complex evaluation process self-managing and scalable to large numbers of consumers and entities
Data Source
AI summary
A method for providing insights based on merchant bidding includes: storing a plurality of transaction data entries, each including a merchant identifier and transaction data; receiving merchant bids, each being received from a different merchant and including a bid amount and corresponding merchant identifier; identifying a transaction metric based on the transaction data included in each transaction data entry; identifying a propensity to transact for each corresponding merchant identifier based on the transaction data included in each transaction data entry that includes the respective corresponding merchant identifier; determining a winning bid of the plurality of merchant bids based on a combination of the propensity to transact for the included corresponding merchant identifier and the included bid amount; and transmitting the account identifier included in the account profile to the merchant from which the winning bid was received.