Payment-Based Item Recommendation System
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing virtual marketplace systems face high processing burdens due to users needing to perform numerous search requests or browse through large lists of irrelevant items to find relevant products, which is inefficient and places a heavy load on servers.
Innovation Solution
A computer-implemented method that uses a virtual persona associated with a payment account to retrieve merchant and item data based on previous payment authorizations, reducing the need for unnecessary item information requests by providing personalized recommendations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If users perform numerous search requests or browse through large lists of items to find relevant products, then users can identify items relevant to their requirements, but servers experience high processing burden and communication overhead
Solution Approach 1:
The system performs preliminary actions by analyzing user payment authorization data before the user makes a search request. Merchant data and item data are pre-fetched and stored based on historical payment patterns, so when a user accesses the virtual marketplace, recommendations are immediately available without requiring extensive real-time processing or multiple search requests.
Solution Approach 2:
The system enables self-service by automatically generating personalized recommendations using the user's own payment authorization history. The server autonomously analyzes the user's spending patterns, identifies preferred merchants and items, and presents relevant recommendations without requiring the user to perform multiple search operations or manually filter through irrelevant items.
2Measurement precision
If users submit specific search criteria such as recipes to narrow down results, then the number of relevant items increases, but user interaction complexity and time requirements increase
Solution Approach 1:
The system performs recommendation generation autonomously by analyzing the user's payment authorization data without requiring the user to manually input search criteria or select recipes. The user simply needs to provide payment authorization, and the system automatically identifies relevant merchants and items based on historical spending patterns.
Solution Approach 2:
The system pre-analyzes user payment data to build a profile of preferred merchants and items before any search is needed. This preliminary analysis eliminates the need for users to manually prepare detailed search criteria during the shopping process.
3Measurement precision
If the system retrieves and displays details of a large number of items to ensure relevance, then users can find relevant products, but communication burden and data transmission overhead increase
Solution Approach 1:
The system extracts only the most relevant information from the user's payment authorization data - specifically, the identifiers of preferred merchants and frequently purchased items. Instead of retrieving and transmitting details of all possible items, the system selectively extracts and transmits only the subset of data that is most likely to be relevant to the user's needs.
Data Source
AI summary
The present disclosure relates to a method and system for providing item recommendations to a user in a virtual marketplace. A virtual persona associated with a primary account number is identified. A merchant data request message requesting merchant data identifying preferred merchants to whom transactions have been made from the first payment account using the PAN is sent to a first remote server. In response, a set of merchant data associated with preferred merchants is received from the first remote server. An item data request message requesting item data associated with the preferred merchants is sent to a second remote server. In response, a set of item data associated with items that are associated with at least one of the preferred merchants is received from the second remote server. A recommendation of at least one of the items is provided to the user.