In processing large-scale user-item data, recommendation systems often face the challenge of information overload, making it critical to improve recommendation accuracy and efficiency. In recent years, deep learning-based recommendation algorithms have gradually become mainstream. However, due to the high sparsity of user-item interaction data, fully leveraging these sparse features to enhance model performance remains a pressing challenge in the field of recommendation systems. In this context, this paper investigates the application of sparse features in the Wide and Deep Learning model, based on the publicly available Book-Crossing dataset. To evaluate model performance, this study compares Random Forest, Gradient Boosting Decision Trees (GBDT), Multilayer Perceptron (MLP), and Wide and Deep Learning models using three metrics: Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Area Under the Curve (AUC). The experimental results demonstrate that the Wide and Deep Learning model outperforms the other models, particularly in terms of AUC and RMSE, confirming its advantages in handling sparse data and improving the performance of recommendation systems.

Guo Jiajie. Enhancing Book Recommendation Systems through the Application of Sparse Features in Wide and Deep Learning Models. International Journal of Frontiers in Engineering Technology (2024), Vol. 6, Issue 5: 106-111. https://doi.org/10.25236/IJFET.2024.060515.

[1] Xu Enyuan. Design of personalized book recommendation system for university libraries[J]. Science & Technology Information, 2023(13): 207-210.

[2] Tu Tie, Liu Bin. Research on collaborative filtering book recommendation algorithm based on clustering and prediction filling[J]. Journal of Guizhou Institute of Technology and Applications, 2024(3): 100-105.

[3] Zhao Jie. Research on personalized book recommendation algorithm based on improved user interest model[J]. Machine Tool & Hydraulics, 2018(6): 193-198.

[4] Ling Yaoyin. Research on the application of personalized recommendation technology in university digital libraries[J]. Information Recording Materials, 2023(10): 79-97.

[5] Yu Chaoyu. Research on differentiated intelligent book recommendation algorithm based on Bayesian network[D]. Master's Thesis, Beijing Jiaotong University, 2022.

[6] Chen Changhua. Research on personalized book recommendation method based on ISODATA clustering algorithm[J]. Software Engineering and Applications, 2022(4): 35-40.

[7] Wang Qianli. Research on book recommendation algorithm based on improved ALS collaborative filtering[J]. Library Science Research, 2021(7): 58-65.

[8] Shi Fengyuan. Design and implementation of book recommendation analysis system based on big data[D]. Master's Thesis, Nanjing University of Science and Technology, 2023.

[9] Yan Fan. Research on book recommendation method based on book semantic information[D]. Master's Thesis, Dalian University of Technology, 2023.

[10] Wang Yuqin. Research on personalized library recommendation system based on hybrid algorithm[J]. Science and Publishing, 2022(10): 23-29.

[11] Wu Simin. Integration of user information needs analysis and personalized book recommendation system[J]. Literature and History Expo, 2023(10): 67-72.

[12] Zhang Huaigao. Research on personalized recommendation scheme for e-book stores based on privacy protection[D]. Master's Thesis, East China Normal University, 2021.

[13] Wang Dafu. Research on personalized book recommendation for university libraries based on user profiling[J]. Journal of Henan Normal University, 2022(3): 95-103.

[14] Bao Yan. Design of personalized book recommendation system based on long- and short-term preferences[J]. Inside and Outside the Lantai, 2024(19): 70-72.

[15] Chen Linghong. Research on book recommendation based on knowledge graphs and reader profiling[D]. Master's Thesis, Huazhong University of Science and Technology, 2023.

[16] Zhong Zufeng. Research on book recommendation algorithm to enhance diversity based on re-ranking[J]. Computer Science, 2023(9): 100-108.

[17] Gao Xia. Application of full-text retrieval technology in book retrieval[J]. Journal of Zhongyuan Institute of Technology, 2024(2): 85-89.

[18] Zheng Xin. Application of collaborative filtering algorithm in book recommendation systems[J]. Journal of Fuzhou Business College, 2023(12): 60-62.

[19] Song Chuping. Application of an improved collaborative filtering method in university library book recommendation[J]. Library and Information Work, 2016(24): 86-91.

[20] Fu Yongping. Research on personalized collaborative filtering recommendation method based on Bayesian network[J]. Journal of Intelligence, 2023(3): 45-53.

[21] Cheng H T, Koc L, Harmsen J, et al. Wide & Deep Learning for Recommender Systems[J]. arXiv preprint arXiv:1606.07792, 2016.