当前位置:网站首页>2022 8th "certification Cup" China University risk management and control ability challenge
2022 8th "certification Cup" China University risk management and control ability challenge
2022-07-07 12:00:00 【Enthusiastic netizen Mr. Minamata】
The start time of this risk control cup is the beginning of summer , This game can also be used as a practice match of the National Games for running in between teammates . The theme of this risk control competition is the current car loan , The title gives the data set of the international market . The title is as follows ,
According to the title requirements , We can see that the topic generally requires us to carry out two steps , One 、 Screening of relevant indicators , Two 、 Establishment of prediction model . Here we explain these two steps separately .
The most critical step before the index processing is our processing of the given data , Because the given data may have outliers , We need to deal with the vacancy value accordingly , The relevant processing code is also summarized for you .
One 、 Relevant index screening
According to the needs of the topic , The first step is to screen out relevant indicators , In order to facilitate our next step of model establishment, solution and related analysis . For the selection of indicators , Here I think there are two ways to screen , Both objective and subjective . namely , We can artificially screen some indicators as preliminary indicators ; At the same time, we can also use correlation analysis 、 Causal analysis screens key indicators . I will share some related codes for you later , I hope I can help you .
Two 、 Establishment of prediction model
Predict whether the lender will default , This problem itself is a problem of establishing predictions based on data . I think there can be multiple linear regression prediction , Time series prediction , Grey prediction , Fuzzy prediction, etc . There is a better way to establish here is to choose two or three prediction models , Finally, compare the accuracy of the results . In this way, our model will be very complete , At the same time, effectively increase the length of the article . The code of the prediction model will be supplemented later .
Final , I wish you all good results in this competition , Be able to run in with your teammates more , Create more brilliance in the National Games .
边栏推荐
- Talk about SOC startup (VII) uboot startup process III
- 顶级域名有哪些?是如何分类的?
- Test the foundation of development, and teach you to prepare for a fully functional web platform environment
- Programming examples of stm32f1 and stm32subeide -315m super regenerative wireless remote control module drive
- C#中在路径前加@的作用
- There are so many factors that imprison you
- UP Meta—Web3.0世界创新型元宇宙金融协议
- 相机标定(2): 单目相机标定总结
- . Net Maui performance improvement
- Network protocol concept
猜你喜欢
[texture feature extraction] LBP image texture feature extraction based on MATLAB local binary mode [including Matlab source code 1931]
Talk about SOC startup (VII) uboot startup process III
STM32F1与STM32CubeIDE编程实例-MAX7219驱动8位7段数码管(基于SPI)
Sonar:Cognitive Complexity认知复杂度
108. Network security penetration test - [privilege escalation 6] - [windows kernel overflow privilege escalation]
Time bomb inside the software: 0-day log4shell is just the tip of the iceberg
Camera calibration (1): basic principles of monocular camera calibration and Zhang Zhengyou calibration
超标量处理器设计 姚永斌 第8章 指令发射 摘录
CMU15445 (Fall 2019) 之 Project#2 - Hash Table 详解
The road to success in R & D efficiency of 1000 person Internet companies
随机推荐
Zhou Yajin, a top safety scholar of Zhejiang University, is a curiosity driven activist
About how to install mysql8.0 on the cloud server (Tencent cloud here) and enable local remote connection
Talk about SOC startup (VI) uboot startup process II
HCIA复习整理
[neural network] convolutional neural network CNN [including Matlab source code 1932]
Tsinghua Yaoban programmers, online marriage was scolded?
超标量处理器设计 姚永斌 第10章 指令提交 摘录
Visual Studio 2019 (LocalDB)\MSSQLLocalDB SQL Server 2014 数据库版本为852无法打开,此服务器支持782版及更低版本
Common locking table processing methods in Oracle
SwiftUI 4 新功能之掌握 WeatherKit 和 Swift Charts
Up meta - Web3.0 world innovative meta universe financial agreement
R language uses the quantile function to calculate the quantile of the score value (20%, 40%, 60%, 80%), uses the logical operator to encode the corresponding quantile interval (quantile) into the cla
111.网络安全渗透测试—[权限提升篇9]—[Windows 2008 R2内核溢出提权]
人大金仓受邀参加《航天七〇六“我与航天电脑有约”全国合作伙伴大会》
In depth learning autumn recruitment interview questions collection (1)
【滤波跟踪】基于matlab扩展卡尔曼滤波EKF和无迹卡尔曼滤波UKF比较【含Matlab源码 1933期】
[full stack plan - programming language C] basic introductory knowledge
. Net Maui performance improvement
总结了200道经典的机器学习面试题(附参考答案)
Superscalar processor design yaoyongbin Chapter 10 instruction submission excerpt