Prediction and Estimation of Book Borrowing in the Library: Machine learning

Abstract

In the library, the prediction and estimation of book borrowing plays an important role in library work. Based on the data mining method, this paper analyzed the prediction and estimation of book borrowing. Firstly, the radial basis function neural network (RBFNN) was analyzed. Then, the improved ant colony algorithm (IACO) was used to obtain the optimal parameters of RBFNN, and then the IACO-RBFNN model was established to realize the prediction and estimation of book borrowing. The results showed that the improved model had advantages in training time, iteration times, and error compared with BPNN and RBFNN. The results of book prediction and estimation showed that the results obtained by the IACO-RBFNN model were closer to the actual book borrowing situation, with smaller error and higher precision (97.09%), and its precision was 11.18% and 4.74% higher than BPNN and RBFNN respectively. The training time and testing time of the IACO-RBFNN model were 5.12 s and 1.03 s, respectively, which were significantly shorter than the other two methods. The results show that the IACO-RBFNN model has a good performance in the prediction and estimation of book borrowing and can be further promoted and applied in practice.