Abstract: The artificial neural network is an information processing system established by imitating the structure and the function of cerebral neuron networks. It is widely used in data processing and analysis of various spectroscopies. Back-propagation neural network is one of the most useful and perspective networks, therefore it is used in quantitative prediction of UV-Vis adsorption spectroscopy and Raman spectroscopy in this paper. The results showed that the prediction accuracy has been remarkably improved compared with linear regression, and the satisfied prediction results were obtained. This provides a method more effective and more accurate for spectroscopic analysis and processing of spectral data.