AI PB: A Grounded Generative Agent for Personalized Investment Insights
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917035920850944 |
|---|---|
| author | Park, Daewoo Park, Suho Hong, Inseok Lee, Hanwool Park, Junkyu Lee, Sangjun An, Jeongman Loh, Hyunbin |
| author_facet | Park, Daewoo Park, Suho Hong, Inseok Lee, Hanwool Park, Junkyu Lee, Sangjun An, Jeongman Loh, Hyunbin |
| contents | We present AI PB, a production-scale generative agent deployed in real retail finance. Unlike reactive chatbots that answer queries passively, AI PB proactively generates grounded, compliant, and user-specific investment insights. It integrates (i) a component-based orchestration layer that deterministically routes between internal and external LLMs based on data sensitivity, (ii) a hybrid retrieval pipeline using OpenSearch and the finance-domain embedding model, and (iii) a multi-stage recommendation mechanism combining rule heuristics, sequential behavioral modeling, and contextual bandits. Operating fully on-premises under Korean financial regulations, the system employs Docker Swarm and vLLM across 24 X NVIDIA H100 GPUs. Through human QA and system metrics, we demonstrate that grounded generation with explicit routing and layered safety can deliver trustworthy AI insights in high-stakes finance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_20099 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AI PB: A Grounded Generative Agent for Personalized Investment Insights Park, Daewoo Park, Suho Hong, Inseok Lee, Hanwool Park, Junkyu Lee, Sangjun An, Jeongman Loh, Hyunbin Artificial Intelligence Computational Engineering, Finance, and Science Computation and Language We present AI PB, a production-scale generative agent deployed in real retail finance. Unlike reactive chatbots that answer queries passively, AI PB proactively generates grounded, compliant, and user-specific investment insights. It integrates (i) a component-based orchestration layer that deterministically routes between internal and external LLMs based on data sensitivity, (ii) a hybrid retrieval pipeline using OpenSearch and the finance-domain embedding model, and (iii) a multi-stage recommendation mechanism combining rule heuristics, sequential behavioral modeling, and contextual bandits. Operating fully on-premises under Korean financial regulations, the system employs Docker Swarm and vLLM across 24 X NVIDIA H100 GPUs. Through human QA and system metrics, we demonstrate that grounded generation with explicit routing and layered safety can deliver trustworthy AI insights in high-stakes finance. |
| title | AI PB: A Grounded Generative Agent for Personalized Investment Insights |
| topic | Artificial Intelligence Computational Engineering, Finance, and Science Computation and Language |
| url | https://arxiv.org/abs/2510.20099 |