The purpose of this study is to develop an efficient performance prediction algorithm to evaluate the performance of experimental technicians in universities. Therefore, we combine the improved Analytic Network Process (ANP) and Back Propagation Neural Network (BPNN) to construct a novel prediction model. In the method, firstly, ANP is improved by introducing fuzzy set theory to determine the weight of each performance index more accurately. Subsequently, these indicators are studied and predicted by using BPNN. The results show that the prediction accuracy of this algorithm is over 95%, and the prediction efficiency is remarkable. The performance prediction algorithm based on improved ANP and BPNN can provide scientific and objective tools for the performance assessment of experimental technicians in universities, and help to improve the efficiency and accuracy of human resource management. This research not only provides new decision support for university administrators, but also provides useful reference for the personal development of experimental technicians.