User age prediction by combining classification and regression}{User age prediction by combining classification and regression

Age classification and age regression are two main approaches of age prediction, and both approaches have their respective advantages. For example, age classification can flexibly utilize distinguished model in machine learning while the main advantage of age regression is its ability to capture the relationship between different ages. In order to utilize advantages of age classification and age regression simultaneously, we propose a hybrid age prediction approach that combines classification and regression. First, we build the long short-term memory (LSTM) models of age regression and age classification respectively for age prediction. Then, we linearly combine the results of the age classifier and age regressor as the final result of age prediction. Empirical evaluations demonstrate that the proposed hybrid model effectively improves the performance.