Graph Community Prediction for Personalized Recommendations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current mobile device applications for locating nearby establishments, such as restaurants, often fail to provide personalized recommendations that cater to individual user preferences, as they cannot anticipate specific user preferences like fast food vs. sit-down restaurants or trendy vs. non-trendy establishments.
Innovation Solution
A method involving the creation of a topological graph based on interaction data between users and resource providers, where communities are determined and a predictive model is formed to identify nodes that match user requests, providing personalized recommendations by analyzing interaction probabilities and weights within these communities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If general query-based search is used to locate nearby establishments, then the system can provide broad coverage of results, but the results do not align with individual user preferences
Solution Approach 1:
The system changes parameters by computing weights for nodes and edges in the graph based on interaction data, and by determining communities with different densities. This allows the system to adapt recommendations to individual user preferences without requiring complex manual configuration, resolving the contradiction between personalization and system complexity
Solution Approach 2:
The system performs self-service by automatically learning user preferences from interaction data and generating personalized recommendations without requiring explicit user input or complex configuration. The graph-based model self-organizes into communities that reflect user preferences, enabling personalization while keeping the system relatively simple
2Measurement precision
If interaction data is analyzed to create personalized recommendations, then prediction accuracy improves, but data processing complexity increases
Solution Approach 1:
The system segments the interaction graph into multiple communities with different densities. This segmentation allows the system to process data more efficiently by working with smaller, focused subsets of the data rather than the entire graph, improving prediction accuracy while managing data processing complexity
Solution Approach 2:
The system applies local quality by computing weights and determining communities with varying densities across different parts of the graph. Each community is optimized for its specific characteristics, allowing the system to achieve high prediction accuracy for different types of interactions without uniformly complex processing across the entire system
Data Source
AI summary
Embodiments of the invention are directed to methods and devices for predicting interactions. One embodiment is directed to a method comprising receiving, by one or more computers, interaction data for a plurality of known interactions between resource providers and users, and creating a topological graph based on the plurality of known interactions. The method may further comprise determining, by the one or more computers, a plurality of communities to form a predictive model, and receiving a request for a prediction. In addition, the method may comprise applying the request to the predictive model, by the one or more computers, by identifying a community in the plurality of communities corresponding to the request, determining a node within the identified community, and providing information regarding the node as the requested prediction.