"Data Mining is not about automation but about a 4 step process which requires extensive and specialized knowledge by the practitioner. This 4 step process is:
1)Identification of the Business Problem
2)Creation of the…"
AnalyticBridge
Data Intelligence, Business Analytics
Richard Boire's Page
Latest Activity
Richard Boire commented on Vincent Granville's blog post What causes predictive models to fail - and how to fix it?
"Your comments and Edmund's comments really hit the nail on the head when it comes to model failure which is really about having proper validations. In our business, we do multiple validations:
1)50/50 where the analytical file…"
Richard Boire replied to Sharath Dandamudi's discussion Handling problem of Multi-collinearity
"Sorry about that. pressed the post button too early. The more experienced approach as opposed to academic approach is as follows:
1)This is only a problem if the actual variable switches in sign in the multivariate routine from what you observe in…"
Richard Boire commented on Tony Agresta's blog post Data Analysis Using Relationship Graphs
"Your post on the visualization theme looks great but I do have one question which is how do these tools perform when you are looking at hundreds of thousands of customers.
"
Richard Boire replied to DataLLigence's discussion Top 10 modeling mistakes
"I have attached an article(DM News in Canada) that I have written which looks at the top ten tips in creating successful predictive analytics solutions. This is a 3 part series with the first article touching on the first three…"
Richard Boire replied to Tom Wolfer's discussion 2011 Canadian Marketing Association Analytics Conference
"Tom, I would not mind touching base with you personally to better understand your career interests within the area of analytics. My company, the Boire Filler Group is a data mining and marketing analytics company, which provides services in this…"
Richard Boire commented on Vincent Granville's blog post The next revolution in analytics: it's not about software, it's about data
"Victor, you are absolutely right. We have always stressed the data with the organizations that we work with. But it's not just external data that we focus on. We will focus on the company's own internal data and arrive at unique approaches…"
Patrick Surry commented on Richard Boire's blog post Net Lift modelling
"Oh, forgot to mention: there were a couple of good talks about uplift at the recent Predictive Analytics World event, including Eric Siegel’s keynote, Andrew Pole's Challenges of Incremental Sales Modeling in Direct Marketing, and Mike…"
Richard Boire's Photos
Richard Boire's Blog
Net Lift modelling
One of the most perplexing data mining dilemmas has to do with building tools that effectively rank order net lift. Essentially, marketers will promote a group but also have a holdout group where there is no marketing treatment. The modelling dilemma is that the net lift or difference in response rate between the marketted group vs. non marketted group is the same across all the deciles when models are typically built against the marketted group. There is software offered by some vendors that… Continue
Posted on October 20, 2009 at 9:23am — 4 Comments
Comment Wall
- No comments yet!
Top Content
Follow us
© 2013 AnalyticBridge.com is a subsidiary and dedicated channel of Data Science Central LLC
