HomeWork ISYE6501x Course Info | EDX


WEEK 1 HOMEWORK

Question 1

Describe a situation or problem from your job, everyday life, current events, etc., for which a classification model would be appropriate. List some (up to 5) predictors that you might use.

I built a mix of descriptive, prescriptive and attribution model that enable management to gain a better understanding of our current client based, revenue predicatbility and prove the customer seccess teams’s impact.

I built a customer Health Success Score (CHS) that I intended to classify our clients in two buckets:

  1. Clients are doing well hence they’re ready to upsell
  2. Client requires attention hence a customer re-onbording campaing needs to be deployed.

Predictors

For a health score to be an effective KPI, it needs to take into consideration several data types and sources, combined into one health score for each customer. The specifics depends on the product/portfolio/service and our customer success program. In this model, I look at five predictors:

  1. Product usage (engagement, usage frequency and key user-actions)
  2. Business Outcomes (is the customer getting end-result they purchased the product for.
  3. Service utilization: Is the customer fully utilizing their product?
  4. Customer Feedback: Subjective feedback by the extended customer experience, care team
  5. Support & Operations

Question 2

 

##INSTALL KERNLAB

library(kernlab)

##Cambiar la dirección de archivos, para que R ubique la base de datos

Basedatos<-read.csv2(“tarea1.csv”, header=T)

Basedatos

attach(Basedatos)

##Indicarle a R que identifique las variables contenidas en la base de datos

data<-cbind(A1,A2,A3,A8,A9,A10,A11,A12,A14,A15,R1)

data

##Verificar que R haya identificado las variables y la totalidad de los datos

dim(data)

##Al correr los dos modelos se presenta el mismo error en los parametros

modelo<-ksvm(data[,1:10],data[,11],type=”C-svc”,kernel=”vanilladot”, C=100,scaled=TRUE)

model1<- ksvm(as.matrix(data[,1:10]),as.factor(data[,11]),type=”C-svc”,kernel=”vanilladot”, C=100,scaled=TRUE)

model2<-ksvm(data[,1:10],data[,11],type=”C-svc”,kernel=”vanilladot”, length = 4, lambda = 0.5, C=100,scaled=TRUE)

model3<- ksvm(as.matrix(data[,1:10]),as.factor(data[,11]),type=”C-svc”,kernel=”vanilladot”, length = 4, lambda = 0.5, C=100,scaled=TRUE)

UNABLE TO CONTINUE AS THE FOLLOWING ERROR IS DISPLAYED:

model <- ksvm(data[,1:10],data[,11],type=”C-svc”,kernel=”vanilladot”,C=100,scaled=TRUE)

Setting default kernel parameters

Question 3

NO PUEDO CONTINUAR CON EL ANALYSIS PUES UN ERROR SE PRESENTA. Unable to perform as an error was generated and I was unable to resolved. It is my first time using R. I WAS UNABLE TO TROUBLE SHOOUT IT

Diana Esparza

Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s