Research on Personalized Financial Product Recommendation by Integrating Large Language Models and Graph Neural Networks

2025/06/06 by Y. X. Zhao, Zhao, Yushang, Yike Peng +8 · 6 citations
Computer Science · Decision Sciences · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Machine Learning in Healthcare #Recommender Systems and Techniques #Stock Market Forecasting Methods

paper · pdf · doi:10.48550/arxiv.2506.05873

openalex publication_date 2025/06/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

With the rapid growth of fintech, personalized financial product recommendations have become increasingly important. Traditional methods like collaborative filtering or content-based models often fail to capture users' latent preferences and complex relationships. We propose a hybrid framework integrating large language models (LLMs) and graph neural networks (GNNs). A pre-trained LLM encodes text data (e.g., user reviews) into rich feature vectors, while a heterogeneous user-product graph models interactions and social ties. Through a tailored message-passing mechanism, text and graph information are fused within the GNN to jointly optimize embeddings. Experiments on public and real-world financial datasets show our model outperforms standalone LLM or GNN in accuracy, recall, and NDCG, with strong interpretability. This work offers new insights for personalized financial recommendations and cross-modal fusion in broader recommendation tasks.

Citations

• A Comprehensive Review of Multi-Agent Reinforcement Learning in Video Games
• Research on E-Commerce Long-Tail Product Recommendation Mechanism Based on Large-Scale Language Models
• CTLformer: A Hybrid Denoising Model Combining Convolutional Layers and Self-Attention for Enhanced CT Image Reconstruction
• Cloud-Based AI Systems: Leveraging Large Language Models for Intelligent Fault Detection and Autonomous Self-Healing
• User Behavior Analysis in Privacy Protection with Large Language Models: A Study on Privacy Preferences with Limited Data
• Personalized Risks and Regulatory Strategies of Large Language Models in Digital Advertising
• Multidimensional precipitation index prediction based on CNN-LSTM hybrid framework
• Automated Parking Trajectory Generation Using Deep Reinforcement Learning
• Data Augmentation Through Random Style Replacement
• II-NVM: Enhancing Map Accuracy and Consistency with Normal Vector-Assisted Mapping
• AI-Driven Prognostics for State of Health Prediction in Li-ion Batteries: A Comprehensive Analysis with Validation
• NeRF-Based defect detection
• SCORE: Story Coherence and Retrieval Enhancement for AI Narratives
• Research on Personalized Medical Intervention Strategy Generation System based on Group Relative Policy Optimization and Time-Series Data Fusion
• Optimized Path Planning for Logistics Robots Using Ant Colony Algorithm under Multiple Constraints
• Intelligent road crack detection and analysis based on improved YOLOv8
• Financial Analysis: Intelligent Financial Data Analysis System Based on LLM-RAG
• Research and Design on Intelligent Recognition of Unordered Targets for Robots Based on Reinforcement Learning
• Research on the Design of a Short Video Recommendation System Based on Multimodal Information and Differential Privacy
• A CT Image Classification Network Framework for Lung Tumors Based on Pre-trained MobileNetV2 Model and Transfer learning, And Its Application and Market Analysis in the Medical field
• Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Survey
• Enhanced Recommendation Combining Collaborative Filtering and Large Language Models
• Learn from Global Correlations: Enhancing Evolutionary Algorithm via Spectral GNN
• Accurate Prediction of Temperature Indicators in Eastern China Using a Multi-Scale CNN-LSTM-Attention model
• Real-Time Prediction for Athletes' Psychological States Using BERT-XGBoost: Enhancing Human-Computer Interaction
• Research on Effectiveness Evaluation and Optimization of Baseball Teaching Method Based on Machine Learning
• CCi-YOLOv8n: Enhanced Fire Detection with CARAFE and Context-Guided Modules
• Real-time Video Target Tracking Algorithm Utilizing Convolutional Neural Networks (CNN)
• Research on reinforcement learning based warehouse robot navigation algorithm in complex warehouse layout
• Application of an ANN and LSTM-based Ensemble Model for Stock Market Prediction
• Contextual Bandits for Unbounded Context Distributions
• Deep Learning-based Anomaly Detection and Log Analysis for Computer Networks
• Research on Splicing Image Detection Algorithms Based on Natural Image Statistical Characteristics
• A Multimodal Fusion Network For Student Emotion Recognition Based on Transformer and Tensor Product
• DARWIN Series: Domain Specific Large Language Models for Natural Science
• Large Language Models as Master Key: Unlocking the Secrets of Materials Science with GPT

Cited by

• Multimodal Foundation Model-Driven User Interest Modeling and Behavior Analysis on Short Video Platforms
• RLHF Fine-Tuning of LLMs for Alignment with Implicit User Feedback in Conversational Recommenders
• Meta-Learning for Cold-Start Personalization in Prompt-Tuned LLMs
• LLM-Augmented Symptom Analysis for Cardiovascular Disease Risk Prediction: A Clinical NLP
• Credit Risk Analysis for SMEs Using Graph Neural Networks in Supply Chain
• Research on Model Parallelism and Data Parallelism Optimization Methods in Large Language Model-Based Recommendation Systems

Related

• CORONA: A Coarse-to-Fine Framework for Graph-based Recommendation with Large Language Models
• Graph Foundation Models for Recommendation: A Comprehensive Survey
• UBER-GNN: A User-Based Embeddings Recommendation based on Graph Neural Networks
• An Automatic Graph Construction Framework based on Large Language Models for Recommendation
• RecMind: LLM-Enhanced Graph Neural Networks for Personalized Consumer Recommendations