基于TCN和LightGBM的供应商主动维护客户构成模型
A Customer Composition Model for Supplier Proactive Maintenance Based on TCN and LightGBM
DOI: 10.12677/MOS.2023.124307, PDF,    科研立项经费支持
作者: 刘 铭, 何利力, 郑军红*：浙江理工大学计算机科学与技术学院，浙江 杭州
关键词: TCN；LightGBM；主动服务；供应链；TCN； LightGBM； Active Service； Supply Chain
摘要: 本文介绍了一种基于TCN和LightGBM的供应商主动维护客户构成模型，旨在解决传统的被动响应式服务无法满足当今竞争激烈市场需求的问题。该模型结合了时间序列分析和机器学习技术，使用TCN捕捉客户订单数据的时间依赖性，同时利用LightGBM学习非时序的复杂关系特征，以快速捕捉市场变化并提高服务体验，让客户既不断货，也不积压，实现“响应性服务”向“感知响应性主动服务”转变。本文的贡献在于提出了一种高效的供应商维护客户构成模型，具有较强的适应性和预测准确性。该模型的应用可以有效地提高供应商的竞争力，满足市场的需求。
Abstract: This article introduces a customer composition model for supplier proactive maintenance based on TCN and LightGBM, aiming to solve the problem that traditional passive responsive services cannot meet the demands of today’s competitive market. The model combines time series analysis and machine learning techniques, using TCN to capture the time dependency of customer order data and utilizing LightGBM to learn non-time series complex relationship features, in order to quickly capture market changes and improve service experience, allowing customers to have continuous supply without inventory pile-up, achieving the transformation from “responsive service” to “per-ceptive responsive proactive service”. The contribution of this article is to propose an efficient sup-plier maintenance customer composition model, which has strong adaptability and prediction ac-curacy. The application of this model can effectively improve the competitiveness of suppliers and meet market demands.
文章引用：刘铭, 何利力, 郑军红. 基于TCN和LightGBM的供应商主动维护客户构成模型[J]. 建模与仿真, 2023, 12(4): 3348-3359. https://doi.org/10.12677/MOS.2023.124307

参考文献

[1] 孙延华, 张冬杰, 曾庆维, 等. 基于GBRT树模型分位数回归预测的CPFR补货方法[J]. 软件导刊, 2019, 18(12): 35-39.
[2] Belgiu, M. and Drăguţ, L. (2016) Random Forest in Remote Sensing: A Review of Applications and Future Direc-tions. ISPRS Journal of Photogrammetry and Remote Sensing, 114, 24-31. [Google Scholar] [CrossRef] 
[3] Smola, A.J. and Schölkopf, B. (2004) A Tutorial on Support Vector Regression. Statistics and Computing, 14, 199-222. [Google Scholar] [CrossRef] 
[4] Friedman, J., Hastie, T. and Tibshirani, R. (2000) Additive Logistic Regression: A Statistical View of Boosting (with Discussion and a Rejoinder by the Authors). The Annals of Statistics, 28, 337-407. [Google Scholar] [CrossRef] 
[5] Candelieri, A., Giordani, I., Archetti, F., et al. (2019) Tuning Hyperparame-ters of a SVM-Based Water Demand Forecasting System through Parallel Global Optimization. Computers & Operations Re-search, 106, 202-209. [Google Scholar] [CrossRef] 
[6] Chen, T. and Guestrin, C. (2016) Xgboost: A Scalable Tree Boosting Sys-tem. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Fran-cisco, 13-17 August 2016, 785-794. [Google Scholar] [CrossRef] 
[7] Ke, G., Meng, Q., Finley, T., et al. (2017) Lightgbm: A Highly Efficient Gradient Boosting Decision Tree. Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS’ 17), Long Beach, 4-9 December 2017, 3149-3157.
[8] 王华勇, 杨超, 唐华. 基于LightGBM改进的GBDT短期负荷预测研究[J]. 自动化仪表, 2018, 39(9): 76-78+82. [Google Scholar] [CrossRef] 
[9] 罗蓉. 基于机器学习的连锁企业销售预测模型研究[D]: [硕士学位论文]. 重庆: 重庆理工大学, 2022.[CrossRef] 
[10] 郭琛. 基于深度学习的时间序列组合预测模型研究[D]: [硕士学位论文]. 南昌: 南昌大学, 2022.[CrossRef] 
[11] Hochreiter, S. and Schmidhuber, J. (1997) Long Short-Term Memory. Neural Computation, 9, 1735-1780. [Google Scholar] [CrossRef] [PubMed]
[12] 杨丽, 吴雨茜, 王俊丽, 等. 循环神经网络研究综述[J]. 计算机应用, 2018, 38(S2): 1-6+26.
[13] Bai, S., Kolter, J.Z. and Koltun, V. (2018) An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling. (Preprint)
[14] 翟剑锋. 基于TCN的时序数据研究[J]. 电子技术与软件工程, 2021(2):196-198.
[15] 张爱枫, 段新宇, 何枭峰. 基于CNN和LightGBM的新型风电功率预测模型[J]. 电测与仪表, 2021, 58(11): 121-127. [Google Scholar] [CrossRef] 

为你推荐