|
|
深度森林融合模型优化高校电子图书采购策略
|
Abstract:
随着高校对电子图书采购需求的明显增加，为提升采购决策效能，文章提出了一种深度森林融合算法，即LightGBM和CatBoost融合为LHGCAT-XDF的优化模型。该模型兼具LightGBM低内存消耗、和CatBoost低时间复杂度的特点。通过实验结果显示，LHGCAT-XDF相较传统机器学习模型在综合性能上更为卓越，有效克服了传统采购模型在精准性和效率方面的限制，为高校图书馆电子图书采购提供可靠的决策支持。
With the evident increase in demand for electronic book procurement in universities, this paper proposes an optimized model, LHGCAT-XDF, by integrating the LightGBM and CatBoost algorithms to enhance the efficiency of procurement decision-making. This model has the characteristics of low memory consumption of LightGBM and low time complexity of CatBoost. Experimental results demonstrate that LHGCAT-XDF outperforms traditional machine learning models in comprehensive performance, effectively overcoming the limitations of traditional procurement models in precision and efficiency. This provides reliable decision support for electronic book procurement in university libraries.
| [1] | Yang, H.J. (2011) Study on Book Purchase Strategy Based on Web Data Mining Technology. 2011 International Con-ference on Control, Automation and Systems Engineering, Singapore, 30-31 July 2011, 311-313.
https://doi.org/10.1109/ICCASE.2011.5997591 |
| [2] | Wang, R.H., Tang, Y. and Li, L. (2012) Application of BP Neural Network to Prediction of Library Circulation. 2012 IEEE 11th International Conference on Cognitive Informatics and Cognitive Computing, Kyoto, 22-24 August 2012, 31-39. https://doi.org/10.1109/ICCI-CC.2012.6311183 |
| [3] | 阎世竞, 庞丽川, 张鹏, 等. 基于统计分析的高校图书采购决策[J]. 图书馆工作与研究, 2011(7): 61-63. |
| [4] | Zhou, Z.H. and Feng, J. (2019) Deep Forest. National Science Review, 6, 74-86. https://doi.org/10.1093/nsr/nwy108 |
| [5] | AlJame, M., Imtiaz, A., Ahmad, I., et al. (2021) Deep Forest Model for Diagnosing COVID-19 from Routine Blood Tests. Scientific Reports, 11, Article No. 16682. https://doi.org/10.1038/s41598-021-95957-w |
| [6] | Dong, L., Qi, J.F., Yin, B.S., et al. (2022) Reconstruction of Subsurface Salinity Structure in the South China Sea Using Satellite Observations: A LightGBM-Based Deep Forest Method. Remote Sensing, 14, Article 3494.
https://doi.org/10.3390/rs14143494 |
| [7] | Ke, G., Meng, Q., Finley, T., et al. (2017) LightGBM: A Highly Efficient Gradient Boosting Decision Tree. 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, December 2017, 3146-3154. |
| [8] | 顾崇寅, 徐潇源, 王梦圆, 等. 基于CatBoost算法的光伏阵列故障诊断方法[J]. 电力系统自动化, 2023, 47(2): 105-114. |
| [9] | Robertson, S. and Zaragoza. H. (2009) The Probabilistic Rele-vance Framework: BM25 and beyond. Foundations and Trends in Information Retrieval, 3, 333-389. https://doi.org/10.1561/1500000019 |
| [10] | 胡陈陈, 吕卫东, 郑江怀, 等. 基于深度森林的在线课程购买行为预测研究[J]. 应用数学进展, 2022, 11(7): 4306-4312. |
