Application of an Optimized SVR Model of Machine Learning

Machine learning is the core of artificial intelligence. It is a fundamental way to the computer intelligence. Support vector machine is one of the important methods in the field of machine learning. It has the advantages of global optimization and strong generalization ability. It has been successfully applied to face recognition, fault diagnosis, financial forecasting and other fields. In this paper, a novel SVR model is proposed to forecast GDP. In the model, The neighborhood rough set (NRS) is used to reduce the index set and the chaotic genetic algorithm (CGA) is adopted to parameters searching in SVR model. Then the novel model NRS-CGA-SVR is established to predict GDP of Anhui province. The results show that the proposed model is better than the other models presented in this paper on forecasting GDP.