Vendor Recommendation Platform Using Payment Data Weighting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing process of determining a vendor for a meeting between multiple participants is inefficient, as it involves multiple communications and resource consumption to find a vendor that meets criteria, leading to unnecessary computing and network resource usage.
Innovation Solution
A vendor recommendation platform that accesses payment data from multiple users, groups vendors based on categories, determines relative weightings, and generates recommendations using machine learning to identify suitable vendors for a meeting based on parameters like time, type, and price range.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If participants exchange multiple communications to decide on a vendor, then the vendor selection meets participant preferences, but computing and network resources are consumed unnecessarily
Solution Approach 1:
The system performs preliminary actions by accessing payment data and determining relative weightings for vendors before the actual vendor selection is needed. The vendor recommendation platform pre-processes payment information, groups vendors into subsets, and calculates relative weightings based on payment quantities and timing, so that when a vendor recommendation is requested, the computationally intensive work has already been completed, avoiding repeated resource consumption during communication iterations
Solution Approach 2:
The system enables self-service by automatically generating vendor recommendations without requiring multiple back-and-forth communications between participants. The vendor recommendation platform autonomously accesses payment data, processes it through grouping and weighting algorithms, and provides a recommended vendor, eliminating the need for human participants to exchange multiple messages to reach a consensus
2Productivity
If one participant selects vendor based on personal preferences, then selection is quick, but it conflicts with other participants' preferences
Solution Approach 1:
The system changes the parameters of vendor selection by transitioning from subjective preference-based selection to objective data-driven selection. Instead of relying on individual participants' subjective preferences, the system uses objective payment data parameters (payment quantities, timing, vendor categories) to determine relative weightings and generate recommendations that reflect actual spending patterns rather than subjective preferences
Solution Approach 2:
The system achieves universality by creating a vendor recommendation mechanism that serves all participants equally. The vendor recommendation platform processes payment data from multiple users, groups vendors into subsets, and determines relative weightings that aggregate information from all participants' payment behaviors, producing a single recommendation that represents the collective pattern rather than any one individual's preference
3Reliability
If iterative communication is used to find a mutually acceptable vendor, then participant agreement is achieved, but time is lost
Solution Approach 1:
The system performs preliminary actions by pre-processing payment data and determining relative weightings before the vendor recommendation is actually needed. The vendor recommendation platform groups vendors into subsets, calculates relative weightings based on payment quantities and timing, and prepares recommendation data in advance, so that when participants need a vendor recommendation, the analytical work is already complete and only the final recommendation generation is needed
Solution Approach 2:
The system introduces an intermediary mechanism - the vendor recommendation platform - that mediates between participants' diverse preferences and produces a consensus recommendation. Instead of participants directly communicating and negotiating with each other (which causes time loss), the intermediary platform automatically processes payment data, determines relative weightings, and generates a recommended vendor that reflects aggregated participant patterns, eliminating the need for iterative communication
Data Source
AI summary
A device may access payment data of a first payment account and a second payment account that are associated with a first user and a second user, respectively, wherein the payment data includes descriptions of payments to vendors. The device may group the vendors into subsets of vendors based on characteristics of the vendors. The device may determine relative weightings for respective vendors within the subsets. The device may receive a request for a vendor recommendation for a meeting between the first user and the second user, wherein the request identifies parameters for the meeting. The device may generate the vendor recommendation for the meeting by identifying candidate vendors based on the parameters for the meeting and selecting one or more of the candidate vendors based on the relative weightings for the respective vendors.