ZeroMat: Solving Cold-start Problem of Recommender System with No Input Data
arXiv:2112.03084 · doi:10.1109/ICISCAE52414.2021.9590668
Abstract
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.
References in corpus (3)
Cited by in corpus (10)
- MovieMat: Context-aware Movie Recommendation with Matrix Factorization by Matrix Fitting
- PoissonMat: Remodeling Matrix Factorization using Poisson Distribution and Solving the Cold Start Problem without Input Data
- Pareto Pairwise Ranking for Fairness Enhancement of Recommender Systems
- The Fallacy of Borda Count Method -- Why it is Useless with Group Intelligence and Shouldn't be Used with Big Data including Banking Customer Services
- Effective Visualization and Analysis of Recommender Systems
- Is Human Culture Locked by Evolution?
- Theoretically Accurate Regularization Technique for Matrix Factorization based Recommender Systems
- LogitMat : Zeroshot Learning Algorithm for Recommender Systems without Transfer Learning or Pretrained Models
- Zeroshot Listwise Learning to Rank Algorithm for Recommendation
- Mitigating Position Bias with Regularization for Recommender Systems