In the digital music landscape, the accuracy and response speed of music recommendation systems (MRS) are crucial for user experience optimization. Traditional MRS often relies on the use of high-performance servers f...In the digital music landscape, the accuracy and response speed of music recommendation systems (MRS) are crucial for user experience optimization. Traditional MRS often relies on the use of high-performance servers for large-scale training to produce recommendation results, which may result in the inability to achieve music recommendation in some areas due to substandard hardware conditions. This study evaluates the adaptability of four popular machine learning algorithms (K-means clustering, fuzzy C-means (FCM) clustering, hierarchical clustering, and self-organizing map (SOM)) on low-computing servers. Our comparative analysis highlights that while K-means and FCM are robust in high-performance settings, they underperform in low-power scenarios where SOM excels, delivering fast and reliable recommendations with minimal computational overhead. This research addresses a gap in the literature by providing a detailed comparative analysis of MRS algorithms, offering practical insights for implementing adaptive MRS in technologically diverse environments. We conclude with strategic recommendations for emerging streaming services in resource-constrained settings, emphasizing the need for scalable solutions that balance cost and performance. This study advocates an adaptive selection of recommendation algorithms to manage operational costs effectively and accommodate growth.展开更多
In most current recommender systems,the goal to accurately predict what people want leads to the tendency to recommend popular items,which is less helpful in revealing user＇s personality,especially to new users.In th...In most current recommender systems,the goal to accurately predict what people want leads to the tendency to recommend popular items,which is less helpful in revealing user＇s personality,especially to new users.In this paper,we propose a heuristic music recommendation method for niche market by focusing on how to identify user＇s personality as soon as possible.Instead of trying to improve algorithm＇s performance on new users by recommending the most popular items,we work on how to make them ＂familiar＂ with the system earlier.The method is more suitable for brand-new users,and gives a hint to solve the cold start problem.In real applications it is better to combine it with a traditional approach.展开更多
文摘In the digital music landscape, the accuracy and response speed of music recommendation systems (MRS) are crucial for user experience optimization. Traditional MRS often relies on the use of high-performance servers for large-scale training to produce recommendation results, which may result in the inability to achieve music recommendation in some areas due to substandard hardware conditions. This study evaluates the adaptability of four popular machine learning algorithms (K-means clustering, fuzzy C-means (FCM) clustering, hierarchical clustering, and self-organizing map (SOM)) on low-computing servers. Our comparative analysis highlights that while K-means and FCM are robust in high-performance settings, they underperform in low-power scenarios where SOM excels, delivering fast and reliable recommendations with minimal computational overhead. This research addresses a gap in the literature by providing a detailed comparative analysis of MRS algorithms, offering practical insights for implementing adaptive MRS in technologically diverse environments. We conclude with strategic recommendations for emerging streaming services in resource-constrained settings, emphasizing the need for scalable solutions that balance cost and performance. This study advocates an adaptive selection of recommendation algorithms to manage operational costs effectively and accommodate growth.
基金supported by the National Natural Science Foundation of China under Grant Nos.60973120,60903073,61003231,61103109,and11105024
文摘In most current recommender systems,the goal to accurately predict what people want leads to the tendency to recommend popular items,which is less helpful in revealing user＇s personality,especially to new users.In this paper,we propose a heuristic music recommendation method for niche market by focusing on how to identify user＇s personality as soon as possible.Instead of trying to improve algorithm＇s performance on new users by recommending the most popular items,we work on how to make them ＂familiar＂ with the system earlier.The method is more suitable for brand-new users,and gives a hint to solve the cold start problem.In real applications it is better to combine it with a traditional approach.
