Subscribe to DSC Newsletter

Himanshu Sinha
  • Male
  • Delhi
  • India
Share on Facebook
Share

Himanshu Sinha's Friends

  • charles alcide
  • Rekha Shenoy
  • tom reilly

Himanshu Sinha's Discussions

Why propensity scores are not working ??

Started this discussion. Last reply by Sagar Diwakar Uparkar Feb 20, 2015. 1 Reply

Hi All ,I've recently  build a predictive data model for a campaign to target  group of customer who can switch from  payment method  "A" to Payment method "B".The idea was to come up with predictive…Continue

Tags: scoring, model, propensity, analytics, campaign

Techniques to address very low event rate for Logistic Regression Model

Started this discussion. Last reply by Zunqiu Chen Aug 10, 2017. 7 Replies

 Hi Folks,I am looking at data form a telecom company and  developing model  to predict an event ( read churn).I am planning to develop GLM using logit link function.The real problem I am facing in…Continue

Tags: Rate, Data, Weighting, Event, Low

 

Himanshu Sinha's Page

Latest Activity

Sagar Diwakar Uparkar replied to Himanshu Sinha's discussion Why propensity scores are not working ??
"Dear Himanshu, Good afternoon. I'm not expert but still, had you seen the distribution of your sample? Is it normal? I mean to say, if few categories having large probability then there is the possibility of such situation occur. Try to change…"
Feb 20, 2015
Wayne G. Fischer, PhD commented on Himanshu Sinha's blog post Why Propensity Scores not working in Campaign Analytics??
"Himanshu, if you have set up your model variables correctly, it may something as simple as having the "0" (won't switch) and "1" (will switch) conditions reversed.  In SAS Institute's JMP the user may define which…"
Jan 3, 2015
Himanshu Sinha posted a discussion

Why propensity scores are not working ??

Hi All ,I've recently  build a predictive data model for a campaign to target  group of customer who can switch from  payment method  "A" to Payment method "B".The idea was to come up with predictive model with payment/usage variables as independent variable and  the event of switch in past is taken as  dependent variable.i) I used logistic regression model for probability  estimation.ii) The  data  is sorted in order of descending probability and  customer's were solicited. iii)  The results…See More
Dec 9, 2014
Himanshu Sinha's blog post was featured

Why Propensity Scores not working in Campaign Analytics??

Hi All ,I've recently  build a predictive data model for a campaign to target  group of customer who can switch from  payment method  "A" to Payment method "B".The idea was to come up with predictive model with payment/usage variables as independent variable and  the event of switch in past is taken as  dependent variable.i) I used logistic regression model for probability  estimation.ii) The  data  is sorted in order of descending probability and  customer's were solicited. iii)  The results…See More
Dec 6, 2014
Himanshu Sinha replied to Steven Finlay's discussion Will Google buy a credit reference agency?
"I believe it logical to think  that Google would buy a credit rating company in future since this notion of Big data data is behind both of them..however if you closely monitor the type of companies Google bought recently , it'll give you…"
Feb 25, 2014
sulabh replied to Himanshu Sinha's discussion Techniques to address very low event rate for Logistic Regression Model
"Just one more point to add: No matter whatever method you use (Traditional Statistical Algorithms Or Machine Learning), equivalent approach would exist (e.g. In Machine Learning, the objective function can be severely penalized for missclassifying…"
Oct 31, 2013
sulabh replied to Himanshu Sinha's discussion Techniques to address very low event rate for Logistic Regression Model
"Hi, Your problem description makes me think about the use of Penalized Likelihood Method (e.g. Firth's method). Please refer to the following link for details. http://www.statisticalhorizons.com/logistic-regression-for-rare-events Hope this…"
Oct 31, 2013
Himanshu Sinha replied to Himanshu Sinha's discussion Techniques to address very low event rate for Logistic Regression Model
"Thanks Ratheen !! I am  trying the other option. Well just to share , this is the second time I am making such a model.  The disadvantage of such a model  ( with  rare event and oversample events )  is , once you use…"
Oct 30, 2013
ratheen chaturvedi replied to Himanshu Sinha's discussion Techniques to address very low event rate for Logistic Regression Model
"HS, Take the second option - oversample and then add an offset to the final result. Calculate the probabilities and see if you can distinguish between churners and non churners at a specified cut off. If it works - you are in good…"
Oct 30, 2013
charles alcide replied to Himanshu Sinha's discussion Techniques to address very low event rate for Logistic Regression Model
"Hi, I wish I could help in such way. I myself using the Link Model to observe and study repeated events . All events are repeated. My sampling study was "Random or Causality" for drawing winning lottery numbers. The term Regression is…"
Oct 29, 2013
Basile Goungetas replied to Himanshu Sinha's discussion Techniques to address very low event rate for Logistic Regression Model
"HV, Please see a paper by Gary King & Langche Zeng entitled "Logistic Regression in Rare Events Data". Basile"
Oct 28, 2013
Himanshu Sinha's discussion was featured

Techniques to address very low event rate for Logistic Regression Model

 Hi Folks,I am looking at data form a telecom company and  developing model  to predict an event ( read churn).I am planning to develop GLM using logit link function.The real problem I am facing in the data is - very low volume (1.6 %) of churners.So seeking advise  on the following ;- What are the possible (bad) outcomes  if I take randomised training sample,  consisting just 1.6 %  churners ?- Should I weight the training  sample to have a event  rate >25% ?-  Any other technique to…See More
Oct 25, 2013
Himanshu Sinha posted a discussion

Techniques to address very low event rate for Logistic Regression Model

 Hi Folks,I am looking at data form a telecom company and  developing model  to predict an event ( read churn).I am planning to develop GLM using logit link function.The real problem I am facing in the data is - very low volume (1.6 %) of churners.So seeking advise  on the following ;- What are the possible (bad) outcomes  if I take randomised training sample,  consisting just 1.6 %  churners ?- Should I weight the training  sample to have a event  rate >25% ?-  Any other technique to…See More
Oct 25, 2013
Himanshu Sinha replied to Himanshu Sinha's discussion How to forecast multiple time series data in the group Analytical Techniques
"@ Tom- Thanks again, Tom , will send you the mail at mentioned  id right away. @ Arun - Thanks Arun.  This is for a project on operation analytics  for a electricity distribution company.  You'll find similar pain areas…"
Mar 29, 2012
Arun replied to Himanshu Sinha's discussion How to forecast multiple time series data in the group Analytical Techniques
"Hello HV, I was just thinking about this problem of yours. I've never myself come across forecast ever for more than one group/cluster/cohort/individual! I would presume you might have to aggregate data to some level before going about…"
Mar 29, 2012
tom reilly replied to Himanshu Sinha's discussion How to forecast multiple time series data in the group Analytical Techniques
"HV, Assuming models is what has the world in a heap of trouble.  Most software systems pick 30 models from a list and that is what you get.  If you got a Rx for your glasses from a  list of 30, would you be happy? We have a tool…"
Mar 29, 2012

Profile Information

Short Bio:
Analytics professional
Field of Expertise:
Business Analytics, Predictive Modeling, Data Mining, Marketing Databases, Statistical Programming, Vizualization, Statistical Consulting, Artificial Intelligence
Years of Experience in Analytical Role:
10
Professional Status:
Technical, Manager, Consultant
Interests:
Finding a New Position, Networking, Other
Industry:
BFSI, Telcom, Machine Learning, Combinatorial Optimization, AI
How did you find out about AnalyticBridge?
Friend

Himanshu Sinha's Blog

Why Propensity Scores not working in Campaign Analytics??

Posted on December 5, 2014 at 4:00am 1 Comment

Hi All ,

I've recently  build a predictive data model for a campaign to target  group of customer who can switch from  payment method  "A" to Payment method "B".

The idea was to come up with predictive model with payment/usage variables as independent variable and  the event of switch in past is taken as  dependent variable.

i) I used logistic regression model for probability  estimation.

ii) The  data  is sorted in order of descending probability…

Continue

Comment Wall

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

Join AnalyticBridge

  • No comments yet!
 
 
 

On Data Science Central

© 2019   AnalyticBridge.com is a subsidiary and dedicated channel of Data Science Central LLC   Powered by

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