Prediction Of Book Borrowing Patterns Using Lstm-Xgboost For Collection Planning  At Uinsu Library

Andri Ismail Sitepu; Zulham Sitorus; Muhammad Iqbal

doi:10.30865/json.v8i1.10190

Authors

Andri Ismail Sitepu Universitas Pembangunan Panca Budi
Zulham Sitorus Universitas Pembangunan Panca Budi
Muhammad Iqbal Universitas Pembangunan Panca Budi

DOI:

https://doi.org/10.30865/json.v8i1.10190

Keywords:

book borrowing prediction, LSTM, XGBoost, hybrid model, library collection planning, time series

Abstract

University libraries face challenges in evidence-based collection planning due to the underutilization of borrowing circulation data. This study proposes a hybrid prediction model that combines Extreme Gradient Boosting (XGBoost) and Long Short-Term Memory (LSTM) to predict book borrowing patterns at the Library of Universitas Islam Negeri Sumatera Utara (UINSU). The proposed approach employs XGBoost to learn relationships among borrowing-related features and generate prediction outputs, which are subsequently used as additional input features for the LSTM model to capture temporal borrowing patterns. The dataset consists of 3,961 physical book borrowing transactions collected between 2024 and 2025. After preprocessing and feature engineering, the data were chronologically sorted and divided into 80% training data and 20% testing data using a time-based split to preserve the temporal sequence. Model performance was evaluated on the testing data using Root Mean Square Error (RMSE) and Mean Absolute Error (MAE). Experimental results demonstrate that the proposed hybrid XGBoost–LSTM model achieved an RMSE of 0.3879 and an MAE of 0.1868, indicating good predictive performance with relatively low error rates. The comparison between actual and predicted borrowing values further shows that the proposed model is capable of capturing borrowing trends effectively. The developed model can serve as the foundation for a Decision Support System (DSS) to support data-driven collection planning and acquisition strategies in academic libraries.

References

[1] J. Saptari, “Implementasi Perpustakaan Cerdas,” Media Inf., vol. 32, no. 1, pp. 38–48, 2023, doi: https://doi.org/10.22146/mi.v32i1.6986.

[2] E. R. Pebriansyah and T. A. Fitri, “PREDICTION OF LIBRARY BOOK BORROWING PATTERNS USING THE,” vol. 7, no. 4, 2025.

[3] M. R. R. Putra and F. Muttakin, “Prediksi Jumlah Pengunjung Perpustakaan Daerah Kabupaten Batang dengan Menggunakan Metode Fuzzy Time Series Chen-Hsu,” J. Math. UNP, vol. 8, no. 1, pp. 110–119, 2023, [Online]. Available: http://ejournal.unp.ac.id/students/index.php/mat ?%0A1.

[4] A. Kumar and Y. T. A., “Proposing a Conceptual Framework for Social Listening in Libraries : A Potential Game Changer to Engage Gen Z and Centennial Users,” DE GRUYTER, vol. 9, no. 20240012, pp. 1–14, 2025, doi: https://doi.org/10.1515/opis-2024-0012.

[5] Y. Prasetya and R. Rahmi, “Pilot Study on User Experience Analysis of Universitas Indonesia Library Website,” Tik Ilmeu J. Ilmu Perpust. dan Inf., vol. 7, no. 1, p. 105, 2023, doi: 10.29240/tik.v7i1.6453.

[6] S. Endarti, “Perpustakaan sebagai Tempat Rekreasi Informasi,” J. Abdi pustaka, vol. 2, no. 1, pp. 23–28, 2022, doi: https://doi.org/10.24821/jap.v2i1.6990.

[7] S. Khademizadeh, Z. Nematollahi, and F. Danesh, “Library and Information Science Research Analysis of book circulation data and a book recommendation system in academic libraries using data mining techniques,” Libr. Inf. Sci. Res., vol. 44, no. 4, p. 101191, 2022, doi: 10.1016/j.lisr.2022.101191.

[8] Z. A. Salam, A. Saiku, and J. L. Buliali, “Prediksi curah hujan dengan model hybrid xgboost- lstm berdasarkan data pengamatan permukaan,” JIPI (Jurnal Ilm. Penelit. dan Pembelajaran Inform., vol. 10, no. 4, pp. 3731–3739, 2025, [Online]. Available: https://jurnal.stkippgritulungagung.ac.id/index.php/jipi

[9] X. Liu, “Machine Learning with Applications Enhanced prediction of karst spring discharge using a hybrid LSTM-XGBoost model optimized with grid search,” Mach. Learn. with Appl., vol. 22, no. September, p. 100740, 2025, doi: 10.1016/j.mlwa.2025.100740.

[10] K. Ito, H. Iima, and Y. Kitamura, “LSTM forecasting foreign exchange rates using limit order book,” Financ. Res. Lett., vol. 47, no. PA, p. 102517, 2022, doi: 10.1016/j.frl.2021.102517.

[11] S. Kasus, P. Susu, and S. Harian, “Perbandingan Kinerja LSTM dan Prophet untuk,” vol. 9, no. 3, pp. 428–435, 2023.

[12] A. Ajder, H. A. A. Hamza, and R. Ayaz, “Wavelet-Enhanced Hybrid LSTM-XGBoost Model for Predicting Time Series Containing Unpredictable Events,” IEEE Access, vol. 13, no. January, pp. 58671–58679, 2025, doi: 10.1109/ACCESS.2025.3556540.

[13] M. Surono et al., “Hybrid XGBoost-SVM Model untuk Sistem Pendukung Keputusan dalam Prediksi Penyakit Diabetes,” vol. 4, no. 3, pp. 443–454, 2025, doi: 10.55123/insologi.v4i3.5410.

[14] A. F. Alkayes and T. Sugihartono, “Perbandingan Algoritma XGBoost dan LSTM dalam Prediksi Harga Saham Tesla Menggunakan Data Tahun 2025 Abstrak Comparison of XGBoost and LSTM Algorithms in Tesla Stock Price Prediction Using 2025 Data Abstract,” vol. 5, no. 6, pp. 1563–1573, 2025.

[15] Z. Sitorus, M. Iqbal, D. Nasution, and R. F. Wijaya, “Penerapan Deep Learning dan Analisis Sentimen terhadap Gap Kompetensi Lulusan Lembaga Pendidikan dan Pelatihan Vokasi terhadap Dunia Kerja dengan Metode Long Short-Term Memory ( LSTM ),” vol. 6, no. 2, pp. 0–11, 2025, doi: 10.47065/bit.v5i2.2029.

[16] X. Deng et al., “Bagging – XGBoost algorithm based extreme weather identification and short-term load forecasting model,” Energy Reports, vol. 8, pp. 8661–8674, 2022, doi: 10.1016/j.egyr.2022.06.072.