Composite Recommendation of Artworks in E-Commerce Based on User Keyword-Driven Correlation Graph Search

With the ever-increasing diversification of people's interests and preferences, artwork has become one most popular commodities or investment goods in E-commerce, it increasingly attracts attention public. Currently, many real-world virtual artworks can be found finding a means to recommend them appropriate users significant task alleviate heavy burden on selection decisions by users. Existing research mainly studies problem single-artwork recommendation while neglecting more practical but complex composite which considerably influences quality experience potential users, especially when they need select set instead single artwork. Inspired this limitation, we put forward novel approach user keyword-driven correlation graph search named ART com-rec . Through , recommender system output (e.g., an solution) E-commerce considering keywords typed indicate his her personalized preferences. Finally, validate feasibility simulated experiments PW dataset.