simmas
04-26-2011, 12:17 PM
was hoping someone had any ideas on building a model on the following.
let's say we have monthly mailings plus a holdout cell over a period of 12 months.
we don't have a direct measure of response other than if they spend or not, we can only measure the number of spenders at mailed vs control level
i want to capture the impact of the mailings as opposed to those that spent vs those that didn't. As i see it, these are 2 separate approaches,
- the latter measures how likely a site is to start spending, which is the natural rate if you like and could be captured in a simple logistic model
- the former, which i am interested in, would measure how much the mailing impacts whether they start spending (if it does at all!)
How would you go about building something to rank sites based on how likely they are to respond to the mailing. In essence to identify the key characteristics (firmagraphics, behaviours etc) that are proving the most responsive to the mailing and to rank a site based on the impact of DM on their response.
as a simple example, i could build a set of indexes at SIC code level for mailing response vs control however this is using some pre-determined level (e.g. industry)... i need to take into account the repeated mailings and a model would also allow the model to determine which items and values (i.e. SIC by empsize) i should use to differentiate.
hope this makes sense
cheers
let's say we have monthly mailings plus a holdout cell over a period of 12 months.
we don't have a direct measure of response other than if they spend or not, we can only measure the number of spenders at mailed vs control level
i want to capture the impact of the mailings as opposed to those that spent vs those that didn't. As i see it, these are 2 separate approaches,
- the latter measures how likely a site is to start spending, which is the natural rate if you like and could be captured in a simple logistic model
- the former, which i am interested in, would measure how much the mailing impacts whether they start spending (if it does at all!)
How would you go about building something to rank sites based on how likely they are to respond to the mailing. In essence to identify the key characteristics (firmagraphics, behaviours etc) that are proving the most responsive to the mailing and to rank a site based on the impact of DM on their response.
as a simple example, i could build a set of indexes at SIC code level for mailing response vs control however this is using some pre-determined level (e.g. industry)... i need to take into account the repeated mailings and a model would also allow the model to determine which items and values (i.e. SIC by empsize) i should use to differentiate.
hope this makes sense
cheers