Accurately predicting recycling prices at battery recycling sites helps reduce transportation and dismantling costs, ensures economies of scale in the recycling, and supports the sustainable development of the new energy vehicle industry. However, this prediction typically relies on easily accessible surface data, such as battery characteristics and market prices. These data have complex correlations with recycling price, general price prediction methods have low prediction accuracy. To this end, an improved prediction method is proposed to enhance the accuracy of predicting recycling prices through surface data. Firstly, factors influencing recycling prices are selected based on self-factor and market fluctuations, a bidirectional denoising autoencoder and support vector regression model (BDAE-SVR) is established. BDAE is used to adjust the weights of influencing factors to remove noise, extract features related to recycling price. The extracted features are introduced into the SVR model to establish a correspondence between the features and recycling price. Secondly, to have better applications for different batteries, the Grey Wolf algorithm (GWO) is used to adjust the SVR parameters to improve the generalization ability of the prediction model. Finally, taking retired power batteries as an example, the effectiveness of the method is verified. Compared with methods such as random forest (RF), the RMSE predicted by BDAE is decreased from 1.058 to 0.371, indicating better prediction accuracy.