Item Reranking Using Query Intent and Cart Context Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems fail to effectively account for user intent and cart context in online shopping, leading to suboptimal item recommendations.
Innovation Solution
A machine learning-based approach that utilizes a ranking model, query model, and cart context model to generate personalized item recommendations by analyzing user session information, including search queries and cart contents, using models like BERT and GBDT to refine item listings.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional recommendation systems are used, then system complexity is low, but recommendation accuracy and relevance to user intent deteriorate
Solution Approach 1:
The recommendation system is segmented into multiple specialized models: a query model for understanding user search intent, a cart context model for analyzing shopping cart data, and a ranking model for generating recommendations. Each model focuses on a specific aspect of user behavior, improving overall recommendation accuracy while maintaining manageable complexity through modular architecture
Solution Approach 2:
The system transitions from traditional single-dimension recommendation approaches to multi-dimensional analysis by incorporating both query intent dimensions and cart context dimensions. This allows the system to analyze user behavior from multiple perspectives simultaneously, enhancing recommendation relevance without proportionally increasing system complexity
2Measurement precision
If user session information is not analyzed, then processing speed is high, but recommendation relevance to user intent deteriorates
Solution Approach 1:
The system performs preliminary analysis of user session information, query data, and cart context before generating recommendations. By pre-processing and understanding user intent and cart contents in advance, the ranking model can quickly generate relevant recommendations without extensive real-time computation, reducing processing time while maintaining high recommendation relevance
3Adaptability or versatility
If cart context is not considered, then computational resources are saved, but personalization of recommendations deteriorates
Solution Approach 1:
The system extracts only the most relevant features from cart context data (such as items already added to cart, category preferences, and shopping patterns) rather than processing entire cart datasets. This selective extraction approach enables personalized recommendations based on cart context while consuming fewer computational resources
Data Source
AI summary
A system including a processor and a non-transitory computer-readable media storing computing instructions that, when executed on the processor, cause the processor to perform operations comprising receiving user session information for a current session for a user; generating, using a ranking model, a first listing of items based on the user session information; generating, using a query model, a query intent measurement based on the user session information; generating, using a cart context model, a cart context measurement based on the user session information; generating a second listing of items based on the first listing of items, the query intent measurement, and the cart context measurement; and displaying the second listing of items in a graphical user interface to the user. Other embodiments are described.