Subscribe to DSC Newsletter

Biswajit Pal
  • Bangalore,Karnataka
  • India
Share on Facebook

Biswajit Pal's Friends

  • Deepak Pareek
  • Kiran Kumar
  • Akash Choudhury
  • Manav Das
  • K.Kalyanaraman
  • Tanushree Mondal
  • Bhaskar Roy
  • Arun
  • Rishi Yadav
  • Vincent Granville

Biswajit Pal's Discussions

Decomposition for log-linear model

Started this discussion. Last reply by Arun Jul 1, 2019. 2 Replies

Hi,  I have estimated a log linear regression model using SAS with the following functional form: lnY = a + XB1 + Xb2 + Xb3 + Xb4 The dependent variable is in log form, the independent/explanatory…Continue

How to reduce high concordance (more than 85) in logistic regression model?

Started this discussion. Last reply by Eric VonDohlen Sep 22, 2010. 4 Replies

HiI am getting a very high concordance in one of my logistic regression model.Can anybody explain the effect of it in the model or why it is not recommended of having a very high concordance and what…Continue

Tags: regression, logistic


Biswajit Pal's Page

Latest Activity

Arun replied to Biswajit Pal's discussion Decomposition for log-linear model
"Hey Bishu!! Long time.. I was pretty much looking for something similar since I ended up doing log-linear for a market mix project.  As far as I can tell, there's no easy way to land at decompositions for a log-linear model. Log…"
Jul 1, 2019

Profile Information

Job Function:
Business Analytics, Predictive Modeling, Data Mining, Biostatistics, Statistical Programming
Short Bio:
I am into Analytics from 2006 onwards. Hold a Master degree in Applied Statistics & Informatics from IIT Bombay. After college I joined an KPO where I worked for a leading healthcare clients in the fields of Time Series , Clustering. Presently I am into Marketing analytics team of a major US retailer working on projects related to logistic regression & other predictive techniques.

Biswajit Pal's Blog

Techniques for solving targeting problem with very low response rate

Posted on May 6, 2011 at 3:42am 0 Comments


I have a population of customer in which 180 out of 5,000,000 is buying a particular product X. Now business wants a list similar to 180 who have the propensity to buy X from the sample so that they can target in future campaigns.

Now as the response rate is low so I am skeptic of using traditional look alike model in this scenario.

Can anyone suggest any technique which can be modeling or data analysis in order to solve this problem?

Thanks for the help in… Continue

Comment Wall

You need to be a member of AnalyticBridge to add comments!

Join AnalyticBridge

  • No comments yet!

On Data Science Central

© 2021   TechTarget, Inc.   Powered by

Badges  |  Report an Issue  |  Privacy Policy  |  Terms of Service