开发者:上海品职教育科技有限公司 隐私政策详情

应用版本:4.2.11(IOS)|3.2.5(安卓)APP下载

aileen20180623 · 2022年12月18日

为啥选b

* 问题详情,请 查看题干

NO.PZ202208300200000303

问题如下:

Given the eventual predictive goal of the model, the best model is:

选项:

A.the current model. B.a random forest model. C.a support vector model.

解释:

Solution

B is correct. Since the defined output, Probability of Default, will be a continuous variable and there is a target variable, Default_Status, then the required model would require the use of regression to solve. Random forest algorithms are a form of continuous supervised models with a target variable.

A is incorrect. The current model is a k-nearest neighbor model, which is a form of supervised classification model for categorical, not continuous, values when the target variable, Default_Status, is defined.

C is incorrect. A support vector model is incorrect because it is a form of supervised classification model used with categorical, not continuous, target variables.

这题为什么不是项量而选随机森林?哪个点看出来的?

1 个答案

星星_品职助教 · 2022年12月19日

同学你好,

SVM是linear classifier,除非有特殊说明,否则都是作为分类来使用的。相比之下,random forest做regression是更优的选择。

----

已多次提示,提问请选择正确的科目标签。

  • 1

    回答
  • 1

    关注
  • 428

    浏览
相关问题

NO.PZ202208300200000303 问题如下 Jain VignetteAmanep Jain is a cret analyst the Entrepreneurship Business velopment Corporation (EB), a government-backeentity thspecializes in proving loans anconsulting services to growing small anmeum-sizeenterprises.Jain sits wn with her colleague, PeirZhang, a recently hireta scientist. They have been asketo work together to velop a machine learning mol to improve EB’s prective ability of intifying potentifaults. The current mol is a k-nearest neighbor (k-NN) mol, whiis useto intify similarities in fault companies anworiginally createwhen the entire portfolio of EB loans wabout 60% of its current level.Jain suggests to Zhang ththe following small changes to the current mol coulincrease its overall prective ability:automating feature selection to improve mol performance,austing hyperparameter k on the basis of the increaseportfolio size, aning aitionnon-financimetrito intify new relationships.Jain tells Zhang ththe “goal” hbeen ancontinues to precting whis storein the system in a fielcallefault_Status, whirecor whether a lois either In fault or Not In fault . Jain incates theventually the mol shoulgenerate a “Probability of fault” between 0% an100% the finoutput for eaclient in the firm’s portfolio.Zhang velops initiprototype anshares with Jithe results baseon a subset of the portfolio thwsegmentefor the purpose of training the mol. Exhibit 1 compares precteanactufaults from the mol.Exhibit 1: Prectevs. ActufaultQuestionGiven the eventuprective goof the mol, the best mol is: A.the current mol. B.a ranm forest mol. C.a support vector mol. SolutionB is correct. Sinthe fineoutput, Probability of fault, will a continuous variable anthere is a target variable, fault_Status, then the requiremol woulrequire the use of regression to solve. Ranm forest algorithms are a form of continuous supervisemols with a target variable.A is incorrect. The current mol is a k-nearest neighbor mol, whiis a form of superviseclassification mol for categorical, not continuous, values when the target variable, fault_Status, is fineC is incorrect. A support vector mol is incorrebecause it is a form of superviseclassification mol usewith categorical, not continuous, target variables. 这个是怎么看出是连续结果的 不是分类吗? 违约或者不违约?

2023-08-30 07:08 1 · 回答