Advertisers within Rakuten’s affiliate network face increasing challenges ensuring that publisher-displayed promotions accurately reflect approved offers. Manual review is time-consuming, inconsistent, and limits scalability. This project presents an automated compliance verification system that integrates Optical Character Recognition (OCR) through Google Cloud Vision API and Generative AI using Gemini 2.5 Flash to extract, validate, and analyze advertisement content at scale. The proposed framework operates in three phases—Extract, Monitor, and Analyse—enabling accurate ad data extraction, automated compliance validation, and relationship analysis through a GraphRAG knowledge graph. The Phase I system achieved a 94–99% accuracy rate while reducing processing time from fifteen minutes to thirty-seven seconds per page. Validation of the GraphRAG model using over fifty question–answer pairs confirmed strong reasoning and retrieval performance. Together, these findings demonstrate that AI-driven automation can significantly improve compliance accuracy, operational efficiency, and strategic insight generation within Rakuten’s global advertising & marketing ecosystem.
Watch the team present this project at 04:18 in the session recording here.
Faculty Advisor
Anil Chaturvedi has over 35 years of professional experience at companies such as AT&T Bell Labs, Kraft Foods, Capital One, and Accenture. He has provided consulting services to Bank of America, Fannie Mae, Johnson & Johnson, and Procter & Gamble. His general research interests include enhancing business value using data science. He has patented and published advanced algorithms for predictive modeling, market segmentation, new product development, product positioning, customer loyalty, consumer promotion mix optimization, and brand strategy. He earned his PhD from Rutgers University and an MBA from IIM Ahmedabad, India.