single-jc.php

JACIII Vol.28 No.5 pp. 1204-1209
doi: 10.20965/jaciii.2024.p1204
(2024)

Research Paper:

Machine Learning Algorithms for Predicting and Estimating Book Borrowing in University Libraries

Huimin Zhang

Library, Handan University
530 North Xueyuan Road, Handan, Hebei 056005, China

Corresponding author

Received:
March 27, 2024
Accepted:
July 31, 2024
Published:
September 20, 2024
Keywords:
university, library, borrowing volume prediction, backpropagation neural network
Abstract

Accurate prediction of borrowing volume of library books is conducive to the decision-making of the managers. This study briefly introduces the backpropagation neural network (BPNN) algorithm used to predict the borrowing volume of university libraries. The factor analysis method and genetic algorithm were employed to optimize the BPNN algorithm to improve its prediction performance. The book borrowing records of 2022 from Handan College Library were considered the subject of simulation experiments. The designed algorithm was compared with the extreme gradient boosting and traditional BPNN algorithms in the experiments. The results showed that average borrowing time, book lending ratio, book return ratio, and average grade of borrowers could be used as the input features of BPNN. The improved BPNN algorithm demonstrated faster convergence and a smaller error during training. The borrowing volume predicted by the improved BPNN algorithm closely matched the actual volume, and the increase in prediction time did not lead to a significant change in the prediction error.

Cite this article as:
H. Zhang, “Machine Learning Algorithms for Predicting and Estimating Book Borrowing in University Libraries,” J. Adv. Comput. Intell. Intell. Inform., Vol.28 No.5, pp. 1204-1209, 2024.
Data files:
References
  1. [1] H. Hu, S. Du, J. Liang, and Z. Kang, “Towards a prediction model of learning performance: informed by learning behavior big data analytics,” Front. Educ. China, Vol.17, pp. 121-156, 2022. https://doi.org/10.3868/s110-007-022-0007-2
  2. [2] N. Muriuki, “Prediction model for book borrowing in universities using neural network,” J. ICT Res. Appl., Vol.12, No.1, pp. 29-34, 2021.
  3. [3] C. Sirikayon, P. Thusaranon, and P. Pongtawevirat, “A collaborative filtering based library book recommendation system,” 2018 5th Int. Conf. on Business and Industrial Research (ICBIR), pp. 106-109, 2018. https://doi.org/10.1109/ICBIR.2018.8391175
  4. [4] T. Silwattananusarn and P. Kulkanjanapiban, “Mining and analyzing patron’s book-loan data and university data to understand library use patterns,” Int. J. Inform. Sci. Manag., Vol.18, No.2, pp. 151-172, 2020.
  5. [5] J. Sun, “Prediction and estimation of book borrowing in the library: Machine learning,” Informatica, Vol.45, No.1, pp. 163-168, 2021. https://doi.org/10.31449/INF.V45I1.3431
  6. [6] J. Wang, L. Zheng, H. Alsulami, and J. Chen, “Modeling and analysis of the book borrowing of students in the library using partial differential equations,” Fractals, Vol.30, No.2, Article No.2240070, 2022. https://doi.org/10.1142/S0218348X22400709
  7. [7] S. Sun, H. Lu, K.-L. Tsui, and S. Wang, “Nonlinear vector auto-regression neural network for forecasting air passenger flow,” J. Air Transp. Manag., Vol.78, pp. 54-62, 2019. https://doi.org/10.1016/j.jairtraman.2019.04.005
  8. [8] Y. He, L. Li, X. Zhu, and K. L. Tsui, “Multi-graph convolutional-recurrent neural network (MGC-RNN) for short-term forecasting of transit passenger flow,” IEEE Trans. on Intelligent Transportation Systems, Vol.23, No.10, pp. 18155-18174, 2022. https://doi.org/10.1109/TITS.2022.3150600
  9. [9] W. Liu, Q. Tan, and W. Wu, “Forecast and early warning of regional bus passenger flow based on machine learning,” Math. Probl. Eng., Vol.2020, No.1, Article No.6625435, 2020. https://doi.org/10.1155/2020/6625435
  10. [10] S. Cai, “Research on the funds forecasting and quality control of book purchasing,” J. Comput. Sci. Appl., Vol.6, No.1, pp. 23-31, 2018. https://doi.org/10.12691/jcsa-6-1-3
  11. [11] W. Cheng, J. M. G. Taylor, T. Gu, S. A. Tomlins, and B. Mukherjee, “Informing a risk prediction model for binary outcomes with external coefficient information,” J. R. Stat. Soc. C: Appl. Stat., Vol.68, No.1, pp. 121-139, 2019. https://doi.org/10.1111/rssc.12306
  12. [12] X. Wang, H. Peng, U. Akram, M. Yan, and S. Attiq, “The effect of successful borrowing times on behavior of investors: An empirical investigation of the P2P online lending market,” Hum. Syst. Manag., Vol.38, No.4, pp. 385-393, 2019. https://doi.org/10.3233/HSM-190517
  13. [13] Z. Xu, Q. Chen, and L. Guo, “Research on the book loan of university library based on the time series theory—Taking Library of Jiangnan University as an example,” J. Libr. Inf. Sci. Agric., Vol.30, No.10, pp. 107-110, 2018 (in Chinese). https://doi.org/10.13998/j.cnki.issn1002-1248.2018.10.019
  14. [14] W. Xie, “Discussion on e-books and library borrowing service,” J. Electron. Res. Appl., Vol.5, No.4, pp. 4-7, 2021. https://doi.org/10.26689/jera.v5i4.2505
  15. [15] Z. M. Tan, T. Fu, and H. Shen, “Research on the dynamic model for book borrowing based on the change of reader groups,” J. Libr. Inf. Sci. Agric., Vol.29, No.2, pp. 114-117, 2017 (in Chinese). https://doi.org/10.13998/j.cnki.issn1002-1248.2017.02.024
  16. [16] K. Baba, T. Minami, and T. Nakatoh, “Predicting book use in university libraries by synchronous obsolescence,” Procedia Comput. Sci., Vol.96, pp. 395-402, 2016. https://doi.org/10.1016/j.procs.2016.08.082
  17. [17] S. Lee, J. Kim, and E. Park, “Can book covers help predict bestsellers using machine learning approaches?,” Telemat. Inform., Vol.78, Article No.101948, 2023. https://doi.org/10.1016/j.tele.2023.101948

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on Nov. 04, 2024