Optimization of XGBoost Credit Risk Prediction Using Swarm Intelligence  Algorithm

doi:10.3778/j.issn.1002-8331.2305-0249

Abstract

Abstract: In order to improve the accuracy of integrated algorithm XGBoost（extreme gradient boosting） in credit risk prediction, an improved sparrow search algorithm（sparrow search algorithm based on golden sine search, Cauchy mutation and opposition-based learning, GCOSSA） is proposed to optimize the parameters.Firstly, the golden sine search strategy is adopted to update the discoverer’s position, which enhances both global and local search ability. Secondly, the opposition-based learning and Cauchy mutation are introduced into the algorithm to expand the search field to find the optimal solution, so as to avoid falling into local optimum, using greedy rules to determine the optimal. Then, the GCOSSA algorithm is tested with 6 benchmark functions, and compared with SSA to evaluate the optimization performance. Finally, the GCOSSA algorithm is used to optimize the parameters of XGBoost. The results show that the GCOSSA algorithm has higher accuracy than the grid search algorithm, the SSA and the ISSA（improved sparrow search algorithm based on sine and cosine） to optimize the parameters of XGBoost in credit risk prediction.

Key words: sparrow search algorithm（SSA）, golden sine search, opposition-based learning, Cauchy mutation, extreme gradient boosting（XGBoost）

摘要： 为改善极端梯度提升（extreme gradient boosting，XGBoost）集成算法的信贷风险预测准确率，提出了一种改进的麻雀算法（improved sparrow search algorithm based on golden sine search，Cauchy mutation and opposition-based learning，GCOSSA）来优化XGBoost参数。采用黄金正弦搜索策略来更新发现者位置，既增强全局搜索能力又增强局部搜索能力；在算法中引入反向学习策略和柯西变异进行扰动来扩大搜索领域改善陷入局部最优，同时使用贪婪规则确定最优解；将改进的算法用6个基准函数进行测试，并对SSA和GCOSSA进行对比，评估GCOSSA寻优性能；用GCOSSA优化XGBoost参数。在数据集上测试，并与网格搜索寻优、SSA及其混合正余弦改进算法（improved sparrow search algorithm based on sine and cosine，ISSA）方法进行对比。结果表明改进后的GCOSSA优化XGBoost参数，在信贷风险预测中准确率更高。

关键词: 麻雀搜索算法, 黄金正弦搜索, 反向学习, 柯西变异, 极端梯度提升（XGBoost）

ZHU Lihua, LONG Haixia. Optimization of XGBoost Credit Risk Prediction Using Swarm Intelligence Algorithm[J]. Computer Engineering and Applications, 2023, 59(23): 305-310.

朱丽华, 龙海侠. 群智能算法优化XGBoost的信贷风险预测[J]. 计算机工程与应用, 2023, 59(23): 305-310.

References

[1] PRISCILLA C V，PRABHA D P.Influence of optimizing XGBoost to handle class imbalance in credit card fraud detection[C]//3rd International Conference on Smart System and Inventive Technology，Tirunelveli，2020：1309-1315.
[2] 王义锋.基于XGBoost+RF的个人信贷风险预测研究[D].重庆：重庆大学，2020.
WANF Y F.Research on personal credit default prediction based on XGBoost+RF[D].Chongqing：Chongqing University，2020.
[3] 王朝辉.基于强化学习和XGBoost的信贷风险预测研究[D].太原：太原理工大学，2022.
WANG Z H.Research on credit risk prediction based on reinforcement learning and XGBoost[D].Taiyuan：Taiyuan University of Technology，2022.
[4] 周芳晔.基于粒子群和XGBoost的银行个人信贷风险预测系统的研究与实现[D].沈阳：辽宁大学，2022.
ZHOU F Y.Research and implementation of bank personal credit risk prediction system based on PSO and XGBoost[D].Shenyang：Liaoning University，2022.
[5] XUE J K，SHEN B.A novel swarm intelligence optimization approach：sparrow search algorithm[J].Systems Science & Control Engineering，2020，8（1）：22-34.
[6] 吕鑫，慕晓冬，张钧，等.混沌麻雀搜索优化算法[J].北京航空航天大学学报，2021，47（8）：1712-1720.
LV X，MU X D，ZHANG J，et al.Chaos sparrow search optimization algorithm[J].Journal of Beijing University of Aeronautics and Astronautics，2021，47（8）：1712-1720.
[7] 张伟康，刘升.自适应t分布与黄金正弦改进的麻雀搜索算法及其应用[J].微电子学与计算机，2022，39（3）：17-24.
ZHANG W K，LIU S.Improved sparrow search algorithm based on adaptive t-distribution and golden sine and its application[J].Microelectronics＆Computer，2022，39（3）：17-24.
[8] 李爱莲，全凌翔，崔桂梅，等.融合正余弦和柯西变异的麻雀搜索算法[J].计算机工程与应用，2022，58（3）：91-99.
LI A L，QUAN L X，CUI G M，et al.Sparrow search algorithm combining sine-cosine and Cauchy mutation[J].Computer Engineering an Applications，2022，58（3）：91-99.
[9] 毛清华，张强.融合柯西变异和反向学习的改进麻雀算法[J].计算机科学与探索，2021，15（6）：1155-1164.
MAO Q H，ZHANG Q.Improved sparrow algorithm combining Cauchy mutation and opposition-based learning[J].Journal of Frontiers of Computer Science and Technology，2021，15（6）：1155-1164.
[10] 张晓萌，张艳珠，刘禄，等.融合多策略的改进麻雀搜索算法[J].计算机应用研究，2022，39（4）：1086-1117.
ZHANG X M，ZHANG Y Z，LIU L，et al.Improved sparrow search algorithm fused with multiple strategies[J].Application Research of Computers，2022，39（4）：1086-1117.
[11] 王海瑞，鲜于建川.改进麻雀搜索算法在分布式电源配置中的应用[J].计算机工程与应用，2021，57（20）：245-252.
WANG H R，XIANYU J C.Application of distributed generation configuration based on improved sparrow search algorithm[J].Computer Engineering and Applications，2021，57（20）：245-252.
[12] 陈深，刘以安，宋海凌.改进麻雀算法在天波雷达定位中的应用[J].激光与光电子学进展，2023，60（10）：350-357.
CHEN S，LIU Y A，SONG H L.Application of improved sparrow algorithm in sky-wave radar location[J].Laser and Optoelectronics Progress，2023，60（10）：350-357.
[13] 周新，邹海.融合黄金正弦混合变异的自适应樽海鞘群算法[J].计算机工程与应用，2021，57（12）：75-85.
ZHOU X，ZOU H.Adaptive salp swarm algorithm with golden sine algorithm and hybrid mutation[J].Computer Engineering and Applications，2021，57（12）：75-85.
[14] 高晨峰，陈家清，石默涵.融合黄金正弦和曲线自适应的多策略麻雀搜索算法[J].计算机应用研究，2022，39（2）：491-499.
GAO C F，CHEN J Q，SHI M H.Multi-strategy sparrow search algorithm integrating golden sine and curve adaptive[J].Application Research of Computers，2022，39（2）：491-499.
[15] 邬贵昌，韦文山，李尚平，等.基于混沌的多策略优化麻雀算法及应用[J].微电子学与计算机，2022，39（12）：21-30.
WU G C，WEI W S，LI S P，et al.Multi-strategy optimization sparrow search algorithm based on chaos and its application[J].Microelectronics & Computer，2022，39（12）：21-30.
[16] 钱晓宇，方伟.基于局部搜索的反向学习竞争粒子群优化算法[J].控制与决策，2021，36（4）：779-789.
QIAN X Y，FANG W.Opposition-based learning competitive particle swarm optimizer with local search[J].Control and Decision，2021，36（4）：779-789.
[17] 邓百川，徐睿，黄成勇，等.基于柯西变异麻雀搜索算法的无人机三维航迹规划[J].机械设计与研究，2022，38（1）：62-66.
DENG B C，XU R，HUANG C Y，et al.Three dimensional flight path planning for unmanned aerial vehicles based on Cauchy mutation sparrow search algorithm[J].Machine Design and Research，2022，38（1）：62-66.
[18] 何庆，林杰，徐航.混合柯西变异和均匀分布的蝗虫优化算法[J].控制与决策，2021，36（7）：1558-1568.
HE Q，LIN J，XU H.Hybrid Cauchy mutation and uniform distribution of grasshopper optimization algorithm[J].Control and Decision，2021，36（7）：1558-1568.
[19] 毛清华，张强，毛承成，等.混合正弦余弦算法和Lévy飞行的麻雀算法[J].山西大学学报，2021，44（6）：1086-1091.
MAO Q H，ZHANG Q，MAO C C，et al.Mixing sine and cosine algorithm with Lévy flying chaotic sparrow algorithm[J].Journal of Shanxi University，2021，44（6）：1086-1091.

Optimization of XGBoost Credit Risk Prediction Using Swarm Intelligence Algorithm

群智能算法优化XGBoost的信贷风险预测

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

[1]	JIA Heming, LIN Jiankai, WU Di, LI Shanglong, WEN Changsheng, RAO Honghua. Modified Chimp Optimization Algorithm Based on Learning Behavior Strategy [J]. Computer Engineering and Applications, 2023, 59(16): 82-92.
[2]	LU Mengdie, LU Haiyan, HOU Xinyu, ZHAO Jinjin, XU Jie. Hybrid Algorithm of Bird Swarm Algorithm and Arithmetic Optimization Algorithm Based on Cauchy Mutation [J]. Computer Engineering and Applications, 2023, 59(14): 62-75.
[3]	OUYANG Chengtian, ZHOU Kai. Teaching-Learning Based Optimization Algorithm with Improved Beetle Antennae Search [J]. Computer Engineering and Applications, 2022, 58(4): 91-99.
[4]	LI Ailian, QUAN Lingxiang, CUI Guimei, XIE Shaofeng. Sparrow Search Algorithm Combining Sine-Cosine and Cauchy Mutation [J]. Computer Engineering and Applications, 2022, 58(3): 91-99.
[5]	MA Chi, ZENG Guohui, HUANG Bo, LIU Jin. Marine Predator Algorithm Based on Chaotic Opposition Learning and Group Learning [J]. Computer Engineering and Applications, 2022, 58(22): 271-283.
[6]	FENG Yunxia, XUE Rongrong. XGBoost_Based Smart Price Model for Ethereum Transactions [J]. Computer Engineering and Applications, 2022, 58(20): 263-269.
[7]	HUANG Qian, LIU Sheng, LI Mengmeng, GUO Yuxin. Multi-Strategy Chimp Optimization Algorithm and Its Application of Engineering Problem [J]. Computer Engineering and Applications, 2022, 58(19): 174-183.
[8]	LUO Shihang, HE Qing. Archimedes Optimization Algorithm Combining Sin Chaos and Segmented Weights [J]. Computer Engineering and Applications, 2022, 58(14): 63-72.
[9]	ZHANG Lin, WANG Tinghua, ZHOU Huiying. Multi-Strategy Improved Sparrow Search Algorithm [J]. Computer Engineering and Applications, 2022, 58(11): 133-140.
[10]	CHEN Gong, ZENG Guohui, HUANG Bo, LIU Jin. HHO Algorithm Combining Mutualism and Lens Imaging Learning [J]. Computer Engineering and Applications, 2022, 58(10): 76-86.
[11]	GUO Yuxin, LIU Sheng, GAO Wenxin, ZHANG Lei. Elite Opposition-Based Learning Golden-Sine Harris Hawks Optimization [J]. Computer Engineering and Applications, 2022, 58(10): 153-161.
[12]	QIU Xingguo, WANG Ruizhi, ZHANG Weiguo, ZHANG Zhaozhao, ZHANG Jing. Improved Whale Optimizer Algorithm Based on Hybrid Strategy [J]. Computer Engineering and Applications, 2022, 58(1): 70-78.
[13]	LI Shouyu, HE Qing, DU Nisuo. Piecewise Weight and Mutation Opposition-Based Learning Butterfly Optimization Algorithm [J]. Computer Engineering and Applications, 2021, 57(22): 92-101.
[14]	WEN Zeyu, XIE Jun, XIE Gang, XU Xinying. Multi-objective Sparrow Search Algorithm Based on New Crowding Distance [J]. Computer Engineering and Applications, 2021, 57(22): 102-109.
[15]	REN Chunhui, LIU Sheng, ZHANG Weikang, ZHANG Weiwei. Optimization and Application of Cauchy Mutation Camel Algorithm [J]. Computer Engineering and Applications, 2021, 57(21): 87-94.