Adaptive methods for job recommendation based on user clustering

Job recommender systems are designed to suggest a ranked list of jobs that could be associated with employee's interest. Most of existing systems use only one approach to make recommendation for all employees, while a specific method normally is good enough for a group of employees. Therefore, this study proposes an adaptive solution to make job recommendation for different groups of user. The proposed methods are based on employee clustering. Firstly, we group employees into different clusters. Then, we select a suitable method for each user cluster based on empirical evaluation. The proposed methods include CB-Plus, CF-jFilter and HyR-jFilter have applied for different three clusters. Empirical results show that our proposed methods is outperformed than traditional methods.