Social Network For Analytic Professionals
-
ANINDO CHAKRABORTY
- Male
- Bangalore,
- India
- Share
- Blog Posts
- Discussions (4)
- Groups (7)
- Photos
- Photo Albums
- Videos
ANINDO CHAKRABORTY's Discussions
Testing for Interactions...
Replied May. 25, 2009
Clustering with non numeric data
Replied May. 4, 2009
ANINDO CHAKRABORTY's Groups
-
Non Parametric Statistics
35 members
-
Time Series
91 members
-
Retail Analytics
26 members
-
SAS Network
294 members
-
Quant Jobs | QUANTster.c…
106 members
ANINDO CHAKRABORTY's Page
Latest Activity
SAS used to supply a CHAID procedure and there was also third party version called SICHAID. I don't know if it's still available. There is a version available within Enterprise Miner, or if you are lucky enough to have SAS/IML installed there is a m…
Well, you can do categorical regression. Gelman and Hill have a good, recent book that's more practically minded than Agresti or Christensen.
You might also look at latent space analysis as is done in Recommender Systems work.
Hi - has anyone worked on clustering project using some non numeric variables? For e.g. clustering customer behavior based on brand preference, type of product purchase etc? I only have SAS EG available with me and couldn't think of a way to do it a…
You can try regression to first weed out insignificant variables...that should substantially prune your variable list. Next, you can check the correlations or conditional indices to tag correlated variables and keep those which have a higher signifi…
Try excel. Create cross tabs taking 2 variables at a time. Note the bad rate differences in each cell. Now group cells with similar (visually) bad rates. You can create 5-8 groups. Now regress by introducing dummy variables to represent these groups…
Would not be my tool of choice, however here is a link to a SOM in Excel
http://www.geocities.com/adotsaha/NN/SOMinExcel.html
-Ralph Winters
please have a look to www.co2alarm.com. It is a clustering application on text mining results. The web site is green-centric but the algorithm is domain independend. It is a small ruby on rails application. What kind of data do you have?
Comment Wall (1 comment)
- At 3:02pm on June 28, 2009,
Bruno M said… - Hi Anindo, I wonder how this project is going? I am relatively new to all of this, and the discussions on this site have been invaluable. I wonder if the tools I suggested (I linked to a list of open source data mining tools, KNIME, Orange (AI Labs), Weka, RapidMinder) have been helpful at all, or whether maybe I was way off on recommending them in the first place (if so i apologize!). Best Regards, Bruno
Profile Information
- Short Bio:
- 7 & 1/2 yrs analytics professional with experience in SAS, Predictive modeling, Developing Classifiers, Analytics Insights.
I began with GE Money working as a risk analyst for credit cards. In this position I built several predictive models making good use out of the logistic regression technique. I also built many segmentation models using CHAID and CART for risk management strategies. I moved out of GE Money after 6 years as a Business Manager in the portfolio risk team. My primary tool was SAS.
I joined a very well renowned retailer in their Analytics team. Here I am a Business Manager leading analytics team for stores, merchandising, finance etc. I have gained more experience in segmentation and modeling techniques for different aspects of retail. I am currently trying to work on some forecasting methods viz. ARIMA. Here too my primary tool is SAS.
My favorite area is classical regression methods. Although there are not many areas where this cannot be used, there are several developments in this field which I try to explore. I am in the process of gaining expertise in forecasting systems.
- Field of Expertise:
- Finance
- Years of Experience in Analytical Role:
- 7.5
- Professional Status:
- Manager
- Interests:
- Finding a New Position, Networking, Recruiting
- Industry:
- Retail
Featured
Advertisement
Analytic Jobs
Most Visited
© 2010 Created by Vincent Granville
