Subscribe to DSC Newsletter

Ravirajan.K
  • Male
  • Noida, Delhi
  • India
Share on Facebook
Share

Ravirajan.K's Friends

  • Chaitanya
  • Gowri Thampi
  • Lance Olson
  • Ravirajan Munnirpallam
  • Payel Bhattacharya
  • Larry
  • Vincent Granville

Ravirajan.K's Discussions

Mean Score Clarification

Started Jan 8, 2013 0 Replies

  Hi, As Iam working on Employee satisfaction survey. I have around 10 pillars and within the pillars 4- 5 questions(attributes). Response scale ranges from 1 to 3 . 1 as disagree, 2 as neutral and 3…Continue

Logistics Data for retail sector

Started this discussion. Last reply by Ravirajan.K Dec 9, 2012. 2 Replies

Hi, I am currently involve in a retail project. Got logistics data of retail firm to indentify the drivers efficiency and to reduce non delivery of products on time.Both indeppendent and dependent…Continue

Interpretation for Tree Classification on R' Packages

Started Apr 23, 2012 0 Replies

Hi friends,Iam currently using R'package to do RF regression method. Dependent variable (Y=1,2,3) and 40 independent variables each sclae from 1 to 5). I have code got node purity for all variables…Continue

How to reduce variables?

Started this discussion. Last reply by Alex Zolot May 26, 2011. 6 Replies

Hi All, Iam currently involved in building a response model for MPE client. sample data set has 3800 variables and 50000 cases. In logistic regression how I can reduce the variables (approx. 2500…Continue

 

Ravirajan.K's Page

Latest Activity

Ravirajan.K posted a discussion

Mean Score Clarification

  Hi, As Iam working on Employee satisfaction survey. I have around 10 pillars and within the pillars 4- 5 questions(attributes). Response scale ranges from 1 to 3 . 1 as disagree, 2 as neutral and 3 as agree. I have calculated weighted mean score for each attribute and pillars.But the problem is eg., average of mean score for all attributes in particular pillar is not matching with that pillar's overall means score.att1 (Pillar 1) 2.56att2 (Pillar 1) 2.38att3 (Pillar 1) 2.58aat4 (Pillar…See More
Jan 8, 2013
Ravirajan.K replied to Ravirajan.K's discussion Logistics Data for retail sector
"Thanks for your suggestion Lance. Dependent variable here is violation in door opening ( "Pass" stage where violation is justified or otherwise) gainst independent variable are engine of truck is on while passing on door or not. GPS has…"
Dec 9, 2012
Lance Olson replied to Ravirajan.K's discussion Logistics Data for retail sector
"Ravirajan, I am not sure I understand the details of your post.  I understand the retail project and you are working on the drivers/delivery to reduce errors and improve efficiency.  And you have captured GPS data. To improve efficiency…"
Dec 9, 2012
Ravirajan.K commented on John A Morrison's blog post R as a Tool in Computational Finance
"i have 8 million records in txt file? can I import into R at one go?"
Dec 5, 2012
Ravirajan.K posted a discussion

Logistics Data for retail sector

Hi, I am currently involve in a retail project. Got logistics data of retail firm to indentify the drivers efficiency and to reduce non delivery of products on time.Both indeppendent and dependent data are binary.(i.e fit for logistic regression). Dependent variable identified was stoppage vehicle in the authorised door (stoppage genuine/ stoppage non genuine) . We have data captured through GPS meter. Could someone suggest me a more about model building? See More
Dec 4, 2012
Ravirajan.K posted a discussion

Interpretation for Tree Classification on R' Packages

Hi friends,Iam currently using R'package to do RF regression method. Dependent variable (Y=1,2,3) and 40 independent variables each sclae from 1 to 5). I have code got node purity for all variables and ordered the variables of importance. As a different approach, I have changed the dependent variable Y= A, B and c instead of 1,2 and 3 with same 40 inde. variables. But in result I got classification and its error rate for A,B and c. additionallty for each variable i got score 9each A,B and C)…See More
Apr 23, 2012
Alex Zolot replied to Ravirajan.K's discussion How to reduce variables?
"in R something like that:   library(randomForest)       rft= tuneRF(Xvars, Yvar, stepFactor=1.2, doBest=T) rfi<- rft$importance;    barplot(rfi[order(- rfi)])  "
May 26, 2011
Ralph Winters replied to Ravirajan.K's discussion How to reduce variables? in the group Business Analytics - Simplified
"Tom and Puneet, Another point I would like to add is that you can use Factor Analysis to simplify things by indicating variables which have no significant loadings on any particular factor.  In these cases variables will simply  drop out…"
Apr 28, 2011
Puneet Agarwal replied to Ravirajan.K's discussion How to reduce variables? in the group Business Analytics - Simplified
"Hi Ralph,   The thing that I have against using the Factor Analysis to reduce the number of predictors is that you would loose the explanatory power of the model. A model built on Factors become very difficult to explain to the business…"
Apr 28, 2011
Puneet Agarwal replied to Ravirajan.K's discussion How to reduce variables?
"I would say Principal component analysis is a good way of reducing the number of variables but the PCAs would not make sense when you try to implement a logistic regression model or to decide the strategies. In my personal experience, It is very…"
Apr 28, 2011
Thomas Ball replied to Ravirajan.K's discussion How to reduce variables? in the group Business Analytics - Simplified
"Ralph-   Thanks for your post.  You are correct in noting that the random trees approach doesn't solve the predictor correlation problem.  It merely develops a greatly shortened scorecard or laundry list of predictors to be…"
Apr 28, 2011
Ralph Winters replied to Ravirajan.K's discussion How to reduce variables? in the group Business Analytics - Simplified
"Tom - I am not understanding your objection to Factor Analysis (or Regression).  Certainly the time taken to understand the relationships in the factors is equivalent to understanding the 100's of decision trees that can be output via the…"
Apr 28, 2011
Mike Olson replied to Ravirajan.K's discussion How to reduce variables?
"I'd also recommend trying principal component analysis.   You could also use a decision tree algorithm (like C4.5) to generate a tree with limited depth, to figure out which variables are giving you the most information.  Then you can…"
Apr 27, 2011
Sandeep Raut replied to Ravirajan.K's discussion How to reduce variables? in the group Business Analytics - Simplified
"there are two methods to reduce variables as you may be aware. Principal component analysis & factor analysis.   for all the technical details you can refer to statsoft text book at…"
Apr 27, 2011
Ravirajan.K replied to DataLLigence's discussion Case Studies in BFSI in the group Case Studies
"Hi ,   Could you please some predictive modelling research paper on automobile analytics. I need to build model based on the available customer pool, who is going to purchase the new cars.. in that way"
Apr 27, 2011
Ravirajan.K replied to David G. Young's discussion The Most Important and Least Thought about Variable: The Dependent in the group Analytical Techniques
"Hi David,   I am working on a project to predict prospect customers for new car. The automobile company has 6 million customer records in their data base  for 2 years ( mostly blank as well). How can I predict the prospe3ct customers?…"
Feb 23, 2011

Profile Information

Field of Expertise:
Business Analytics, Operations Research, Econometrics, Environmental Statistics
Years of Experience in Analytical Role:
6.1
Professional Status:
Technical, Manager
Interests:
Finding a New Position, Networking
Your Company:
IBM India Pvt Ltd
Industry:
KPO
How did you find out about AnalyticBridge?
Friend

Comment Wall

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

Join AnalyticBridge

  • No comments yet!
 
 
 

Follow Us

On Data Science Central

On DataViz

On Hadoop

© 2017   AnalyticBridge.com is a subsidiary and dedicated channel of Data Science Central LLC   Powered by

Badges  |  Report an Issue  |  Terms of Service