Basket Recommendation

Basket recommendation aims to predict items a user will purchase next, either completing a current basket or anticipating future purchases, significantly impacting e-commerce and personalized shopping experiences. Recent research focuses on improving recommendation accuracy by addressing complexities like multiple shopping intentions and handling higher-order item dependencies using advanced models such as neural pattern associators, hypergraph convolutional networks, and transformer-based architectures. These advancements strive to mitigate biases, such as favoring frequently purchased items, and to enhance model efficiency for real-time applications and data privacy concerns, ultimately leading to more relevant and sustainable recommendations.