Lotte Innovate said on the 1st that it built Lotte Department Store's brand data analysis system, "Brand AI," using artificial intelligence (AI) and data technology.
Brand AI is an AI work platform that consolidates and structures sales, customer, and purchase data for about 4,000 brands in line with business context. It supports merchandise planners' (MDs) decision-making—such as store entry and exit and brand sourcing—by analyzing not only individual figures but also relationships and characteristics among brands. It applies an ontology-based data framework that analyzes by consolidating relationships among data.
Lotte Innovate consolidates brand-by-brand sales, customer characteristics, and related purchase data into a graph structure and analyzes brand similarity and cross-purchase relationships based on it. The analysis results are visualized as 2D and 3D network graphs.
It also implemented a "Brand DNA" feature that structures growth potential, customer characteristics, sales scale, and other factors for each brand into six key indicators, and normalizes each indicator on a 0–100 scale to enable comparison of brand characteristics.
For Generative AI features, it applied large language model (LLM) and retrieval-augmented generation (RAG) technologies. It is configured to have AI search and reference relevant data and automatically generate key attributes and characteristics of brands.
Jeon Sung-nyeong, executive director of the D&AX Division at Lotte Innovate, said, "This project is meaningful in that it built a service with high on-site utility by combining Lotte Department Store's MD expertise and field experience with Lotte Innovate's ontology and AI technologies."