Abstract
The present disclosure relates to a multi-agent platform for real-time card-linked offer orchestration. This platform includes a Customer Intent Agent, which predicts a cardholder's purchasing behavior by analyzing transaction history, behavioral signals, and location context. The Merchant Strategy Agent determines optimal discount levels and budget allocation according to merchant goals and market conditions. An Offer Ranking Agent generates a ranked list of offers based on customer relevance scores and predicted redemption probabilities. A Bank Engagement Agent selects the optimal time, channel, and message format for notifying the cardholder of offers based on their notification history. Finally, a Learning and Feedback Agent enhances platform performance by updating models based on offer redemption outcomes and user interactions. The coordinated actions of these agents provide personalized, context-aware offer recommendations tailored to cardholder preferences, thereby improving engagement and redemption rates.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Mishra, Soumendra Kumar; Sharma, Isha; Bansal, Deepak; and Gopal, Kishan, "MULTI-AGENT SYSTEM FOR REAL-TIME PERSONALIZATION OF CARD-LINKED OFFERS", Technical Disclosure Commons, ()
https://www.tdcommons.org/dpubs_series/11997