随着中国新能源汽车的兴起,关于汽车保险诈骗的问题日益突出。为了对保险诈骗行为进行有效识别,本文基于机器学习的相关理论,利用模拟退火算法调参的Stacking融合模型对保险欺诈进行预测。首先,利用随机森林和XGBoost算法筛选得到两个...随着中国新能源汽车的兴起,关于汽车保险诈骗的问题日益突出。为了对保险诈骗行为进行有效识别,本文基于机器学习的相关理论,利用模拟退火算法调参的Stacking融合模型对保险欺诈进行预测。首先,利用随机森林和XGBoost算法筛选得到两个不同特征的训练数据集,然后通过差异化的数据来优化Stacking模型的预测能力,并利用交叉验证法得到最优模型,其准确率为87.43%。实证分析表明,相较于未使用差异化数据的Stacking模型,本文所建的融合模型对汽车保险欺诈行为有更高的识别能力。With the rise of new energy vehicles in China, the issue of car insurance fraud has become increasingly prominent. In order to effectively identify fraudulent insurance activities, this study employs the Stacking ensemble model, optimized using simulated annealing algorithm tuning based on machine learning theories, to predict insurance fraud. Initially, utilizing the Random Forest and XGBoost algorithms, two distinct feature sets are selected to construct training datasets. Subsequently, by employing differentiated data, the predictive capability of the Stacking model is enhanced. Through cross-validation, the optimal model is obtained and its accuracy is 87.43%. Empirical analysis shows that compared to the Stacking model without differentiated data, the ensemble model developed in this study exhibits superior capability in identifying fraudulent behaviors in car insurance.展开更多
针对北京市通州区缺乏生态基流的相关研究,本文以通州区主要河流为研究对象,基于MIKE11模型模拟2019年主要河流氨氮变化特征,并在5个国家级和市级考核监测断面采用水文学法和模型模拟分析城市河道生态基流。结果表明:北运河上游年均氨...针对北京市通州区缺乏生态基流的相关研究,本文以通州区主要河流为研究对象,基于MIKE11模型模拟2019年主要河流氨氮变化特征,并在5个国家级和市级考核监测断面采用水文学法和模型模拟分析城市河道生态基流。结果表明:北运河上游年均氨氮浓度为III类;凉水河、潮白河上段以及北运河中下游为IV类;凤港减河、港沟河及潮白河下段为V类。除王家摆、许各庄断面外,其余断面两种生态基流计算方法的结果较为接近。运潮减河入潮白河口生态基流推荐值为5.5 m3/s、北运河王家摆7.44 m3/s、凉水河许各庄8.83 m3/s、凤港减河小屯4.27 m3/s,港沟河后元化2.97 m3/s。各生态基流保障率均值为89%~100%,基本满足设计保障率要求。本研究对北京市通州区生态基流开展了尝试性的研究工作,为水环境管理提供技术支撑。In view of the lack of ecological base flow in Tongzhou District of Beijing, the main rivers in Tongzhou District were taken as the research object, and the changes of ammonia nitrogen in the main rivers in 2019 were simulated based on the MIKE11 model, while the ecological base flow of urban river was analyzed by hydrologic method at 5 national and municipal examination and monitoring sections. The results show that the annual average ammonia nitrogen concentration in the upper reaches of the Beiyun River was class III;the Liangshui River, the upper part of the Chaobai River, and the middle and lower reaches of the Beiyun River were class IV;the Fenggangjian River, the Ganggou River, and the lower part of the Chaobai River were class V. The calculation results of the two methods are close to each other except Wangjiabai and Xugezhuang. The recommended values of ecological base flow are as follows: 5.5 m3/s at Yunchaojian River, 7.44 m3/s at Wangjiabai, 8.83 m3/s at Xugezhuang, 4.27 m3/s at Xiaotun and 2.97 m3/s at Houyuanhua. The average guarantee rate of ecological base flow is 89%~100%, which basically meets the requirement of design guarantee rate. The ecological base flow studied in Tongzhou District of Beijing will provide technical support for water environment management.展开更多
文摘随着中国新能源汽车的兴起,关于汽车保险诈骗的问题日益突出。为了对保险诈骗行为进行有效识别,本文基于机器学习的相关理论,利用模拟退火算法调参的Stacking融合模型对保险欺诈进行预测。首先,利用随机森林和XGBoost算法筛选得到两个不同特征的训练数据集,然后通过差异化的数据来优化Stacking模型的预测能力,并利用交叉验证法得到最优模型,其准确率为87.43%。实证分析表明,相较于未使用差异化数据的Stacking模型,本文所建的融合模型对汽车保险欺诈行为有更高的识别能力。With the rise of new energy vehicles in China, the issue of car insurance fraud has become increasingly prominent. In order to effectively identify fraudulent insurance activities, this study employs the Stacking ensemble model, optimized using simulated annealing algorithm tuning based on machine learning theories, to predict insurance fraud. Initially, utilizing the Random Forest and XGBoost algorithms, two distinct feature sets are selected to construct training datasets. Subsequently, by employing differentiated data, the predictive capability of the Stacking model is enhanced. Through cross-validation, the optimal model is obtained and its accuracy is 87.43%. Empirical analysis shows that compared to the Stacking model without differentiated data, the ensemble model developed in this study exhibits superior capability in identifying fraudulent behaviors in car insurance.
文摘针对北京市通州区缺乏生态基流的相关研究,本文以通州区主要河流为研究对象,基于MIKE11模型模拟2019年主要河流氨氮变化特征,并在5个国家级和市级考核监测断面采用水文学法和模型模拟分析城市河道生态基流。结果表明:北运河上游年均氨氮浓度为III类;凉水河、潮白河上段以及北运河中下游为IV类;凤港减河、港沟河及潮白河下段为V类。除王家摆、许各庄断面外,其余断面两种生态基流计算方法的结果较为接近。运潮减河入潮白河口生态基流推荐值为5.5 m3/s、北运河王家摆7.44 m3/s、凉水河许各庄8.83 m3/s、凤港减河小屯4.27 m3/s,港沟河后元化2.97 m3/s。各生态基流保障率均值为89%~100%,基本满足设计保障率要求。本研究对北京市通州区生态基流开展了尝试性的研究工作,为水环境管理提供技术支撑。In view of the lack of ecological base flow in Tongzhou District of Beijing, the main rivers in Tongzhou District were taken as the research object, and the changes of ammonia nitrogen in the main rivers in 2019 were simulated based on the MIKE11 model, while the ecological base flow of urban river was analyzed by hydrologic method at 5 national and municipal examination and monitoring sections. The results show that the annual average ammonia nitrogen concentration in the upper reaches of the Beiyun River was class III;the Liangshui River, the upper part of the Chaobai River, and the middle and lower reaches of the Beiyun River were class IV;the Fenggangjian River, the Ganggou River, and the lower part of the Chaobai River were class V. The calculation results of the two methods are close to each other except Wangjiabai and Xugezhuang. The recommended values of ecological base flow are as follows: 5.5 m3/s at Yunchaojian River, 7.44 m3/s at Wangjiabai, 8.83 m3/s at Xugezhuang, 4.27 m3/s at Xiaotun and 2.97 m3/s at Houyuanhua. The average guarantee rate of ecological base flow is 89%~100%, which basically meets the requirement of design guarantee rate. The ecological base flow studied in Tongzhou District of Beijing will provide technical support for water environment management.
