期刊文献+
共找到5篇文章
< 1 >
每页显示 20 50 100
基于CatBoost用信预测模型的TreeSHAP解释性研究 被引量:3
1
作者 马朔 李钊 赵军 《计算机系统应用》 2023年第3期338-344,共7页
银行客户申请信用贷款在授信通过后,精准预测客户是否用信及分析影响客户用信的关键因素,对提高银行客户服务能力及盈利能力具有重要意义.目前,机器学习算法鲜有在用信预测方面的应用,且金融用信领域缺乏模型可解释性的研究,为此提出一... 银行客户申请信用贷款在授信通过后,精准预测客户是否用信及分析影响客户用信的关键因素,对提高银行客户服务能力及盈利能力具有重要意义.目前,机器学习算法鲜有在用信预测方面的应用,且金融用信领域缺乏模型可解释性的研究,为此提出一种基于CatBoost的TreeSHAP解释性用信预测模型.通过CatBoost构建用信预测模型,利用3种超参数优化算法对该模型进行对比优化,与基线模型在4项主要性能指标上进行实验对比,结果表明经TPE算法优化后的模型性能均优于其他模型,然后结合TreeSHAP方法从全局和局部的层面增强模型的可解释性,解释性分析客户用信的影响因素,为银行对客户进行精准化营销提供决策依据. 展开更多
关键词 用信预测 可解释性 TPE CatBoost TreeSHAP 机器学习
下载PDF
Advances of Bioinformatics Tools Applied in Virus Epitopes Prediction 被引量:7
2
作者 Simon Rayner 《Virologica Sinica》 SCIE CAS CSCD 2011年第1期1-7,共7页
In recent years,the in silico epitopes prediction tools have facilitated the progress of vaccines development significantly and many have been applied to predict epitopes in viruses successfully. Herein,a general over... In recent years,the in silico epitopes prediction tools have facilitated the progress of vaccines development significantly and many have been applied to predict epitopes in viruses successfully. Herein,a general overview of different tools currently available,including T cell and B cell epitopes prediction tools,is presented. And the principles of different prediction algorithms are reviewed briefly. Finally,several examples are present to illustrate the application of the prediction tools. 展开更多
关键词 EPITOPE BIOINFORMATICS Epitope prediction algorithms
下载PDF
A NEW ADMISSION CONTROL APPROACH BASED ON PREDICTION
3
作者 Lu Kaining Jin Zhigang Zou Jun(School of Electronic Information Engineering, Tianjin University, Tianjin 300072) 《Journal of Electronics(China)》 2002年第2期209-214,共6页
Admission control plays an important role in providing QoS to network users. Motivated by the measurement-based admission control algorithm, this letter proposed a new admission control approach for integrated service... Admission control plays an important role in providing QoS to network users. Motivated by the measurement-based admission control algorithm, this letter proposed a new admission control approach for integrated service packet network based on traffic prediction. In the letter, FARIMA(p, d, q) models in the admission control algorithm is deployed. A method to simplify the FARIMA model fitting procedure and hence to reduce the time of traffic modeling and prediction is suggested. The feasibility-study experiments show that FARIMA models which have less number of parameters can be used to model and predict actual traffic on quite a large time scale. Simulation results validate the promising approach. 展开更多
关键词 Admission control Traffic prediction FARIMA
下载PDF
High Throughput Satellite System Capacity Analysis and Application Forecast 被引量:2
4
作者 DENG Heng PENG Fei +2 位作者 YUAN Jun SHEN Yufei Pan Ji 《Aerospace China》 2016年第4期30-40,共11页
With the development of large numbers broadband Internet access,global satellite communications is moving towards High Throughput Satellites(HTS).Now,USA,Canada,Europe,Thailand,Japan,United Arab Emirates,Australia hav... With the development of large numbers broadband Internet access,global satellite communications is moving towards High Throughput Satellites(HTS).Now,USA,Canada,Europe,Thailand,Japan,United Arab Emirates,Australia have already developed HTS systems.However,there is little research to analyze the factors influencing high throughput.Thus,from the design perspective,the throughput of HTS and influencing factors are calculated and compared at a system level.Finally,the application of HTS is analyzed and forecasted. 展开更多
关键词 HTS Ka broadband telecommunication satellite Q/V band
下载PDF
Personal Credit Risk .Scoring Model Based on Rough Set and Neural Network
5
作者 Hui Lu Shangfeng Yao 《Journal of Systems Science and Information》 2008年第4期307-314,共8页
In order to improve the precision of personal credit risk assessment, applying rough set and neural network to the credit risk scoring prediction problem in an attempt to suggest a new model with better classification... In order to improve the precision of personal credit risk assessment, applying rough set and neural network to the credit risk scoring prediction problem in an attempt to suggest a new model with better classification accuracy. To evaluate the prediction accuracy of the model, we compare its performance with those of SVM, linear discriminate analysis, logistic regression analysis, K-nearest neighbors, classification and regression tree, neural network and PCA-NN. The experimental results show the model have a very good prediction accuracy 展开更多
关键词 credit risk credit risk assessment rough set neural network 5-fold cross-validation
原文传递
上一页 1 下一页 到第
使用帮助 返回顶部