ZeroMat: Solving Cold-start Problem of Recommender System with No Input Data
This addresses the cold-start problem for industrial practitioners in E-commerce, offering a solution without needing initial data, though it appears incremental as it builds on existing matrix factorization methods.
The paper tackles the cold-start problem in recommender systems by proposing ZeroMat, a technique that requires no input data and achieves competitive Mean Absolute Error and fairness metrics compared to classic matrix factorization with abundant data, while outperforming random placement.
Recommender system is an applicable technique in most E-commerce commercial product technical designs. However, nearly all recommender system faces a challenge called the cold-start problem. The problem is so notorious that almost every industrial practitioner needs to resolve this issue when building recommender systems. Most cold-start problem solvers need some kind of data input as the starter of the system. On the other hand, many real-world applications place popular items or random items as recommendation results. In this paper, we propose a new technique called ZeroMat that requries no input data at all and predicts the user item rating data that is competitive in Mean Absolute Error and fairness metric compared with the classic matrix factorization with affluent data, and much better performance than random placement.