# AnalyticBridge

A Data Science Central Community

Sandeep Sunkara
• Male
• India

## Sandeep Sunkara's Discussions

### Scaling the PD wrt Performance Period

Started Jan 5, 2012

I have built a PD model with the "Ever 90+ in 12 months of Performance Period" as Bad. Now I would like to derive PD for 6 months from the above, still Bad being "Ever 90+" but in 6 months of…Continue

### SAS Program

Started Jun 10, 2011

DATA NEW;ARRAY A[10] A1-A10;ARRAY B[10] B1-B10;DO I = 1 TO 10;A[I] = ROUND(RANUNI(2));END;DO I = 1 TO 10;B[I] = MAX(OF A[1]-A[I]);END;RUN; I get an error using MAX function with arrays, any idea on…Continue

# Sandeep Sunkara's Page

## Latest Activity

"I assume you use logistic regression post applying WOE transformation(?)! X: Independent Variable Y: Binary Dependent Variable T(.): Transformation function  The fundamental assumption in logistic regression is 'X' and…"
Mar 24, 2012
Sandeep Sunkara posted a discussion

### Scaling the PD wrt Performance Period

I have built a PD model with the "Ever 90+ in 12 months of Performance Period" as Bad. Now I would like to derive PD for 6 months from the above, still Bad being "Ever 90+" but in 6 months of performance.PD_90P_12 = Probability of becoming 90+ in next 12 months;PD_90P_06 = f(PD_90P_12) = Probability of becoming 90+ in next 06 months;How will I get the function "f";Any inputs? most welcome and thanks a lot!!See More
Jan 5, 2012
"There is Cubic Clustering Criterion (CCC) available in PROC CLUSTER which helps in deciding the number of clusters.  @Vincent: I am little confused in going up to 4th derivative, since the plot is, when you smooth it, a second degree curve,…"
Oct 3, 2011
"Assuming no inter-dependency among the independent variables, checkout the correlations between target and each characteristic in both earlier time frame and current time frame. The variables that have drastic change in correlation over both the…"
Sep 19, 2011
"Hi Panchanana, For your first question, Variable Reduction for Numerical Variables can be done in two ways: 1. Before the Cluster Analysis(which again can be done in two ways):     (a) Use top N(choose as per the variation explained by the…"
Jun 11, 2011
Sandeep Sunkara posted a discussion

### SAS Program

DATA NEW;ARRAY A[10] A1-A10;ARRAY B[10] B1-B10;DO I = 1 TO 10;A[I] = ROUND(RANUNI(2));END;DO I = 1 TO 10;B[I] = MAX(OF A[1]-A[I]);END;RUN; I get an error using MAX function with arrays, any idea on what is wrong in the above code?See More
Jun 10, 2011
"Yes it is. If you have event rate of 10%, then the predicted probabilities will cluster around 0.1 and hence the cut-off point will also be arount 0.1. If you have event rate of 70%, then the predicted probabilities will cluster around 0.7 and hence…"
Feb 15, 2011

## Profile Information

Field of Expertise:
Predictive Modeling, Data Mining, Statistical Programming, Statistical Consulting
Years of Experience in Analytical Role:
3
Professional Status:
Technical
Interests:
Finding a New Position, Networking
Industry:
BFSI
How did you find out about AnalyticBridge?
Random Browsing