In order to effectively and precisely predict the remanufacturing cost, a remanufacturing cost prediction model based on improved BP neural network was developed. The composition analysis of remanufacturing cost was carried out, and the Decision Making Trial Evaluation Laboratory (DEMATEL)method was used to identify the key influencing factors; on this basis, the improved BP Neural Network method based on particle swarm optimization was used to realize cost prediction; the feasibility of the presented model was verified through the case study. The results show that the proposed method can be used to predict the remanufacturing cost accurately. It provides reference for the remanufacturability evaluation of end-of-life products