5
$\begingroup$

I’d like to ask about a case when we would like to predict the best class of some input variable, so that the probability of event will be maximized.

For example the advertisement type for a given customer, which will maximize the probability of purchase. In collected data we have many various ad types, customer descriptors and informations if the purchase was made or not.

One solution which comes to my mind is to treat the ad type as an input variable, train regular probability model, then make predictions with all ad type configuration and then pick one giving the best estimation.

What are the other options?

$\endgroup$
  • $\begingroup$ Train a classifier with the advertisement type as a categorical variable, and do what you said. And welcome to the site! $\endgroup$ – Emre Apr 3 '18 at 16:49
0
$\begingroup$

If you want to predict the best class of input variable, why don't you take the input variable itself as the output? And say the probability or a boolean of whether the event is happening or not as a input. I guess with enough training data, it may predict right. But that might not be an ideal solution, since you already specify the model the best class for which the event happens, so your approach is a better one.

|improve this answer|||||
$\endgroup$
  • $\begingroup$ Thanks for the response. I don't fully see Your point though. How would You like to forecast the new customer in that case? Set the probability / event input variable to 1 and assume that model therefore suggest the class only associated with events? $\endgroup$ – user73749 Mar 4 '18 at 11:41
  • $\begingroup$ That's why I said the solution is not ideal, maybe not even useful Yes when the event variable is 1, the model suggests the class only associated with events, the output class is suggested based on other features. So the best class for the event may not be the output. $\endgroup$ – Srihari Mar 5 '18 at 17:30
0
$\begingroup$

As you are looking for a conditional distribution of a variable given another one, graphical models come to mind.

|improve this answer|||||
$\endgroup$
0
$\begingroup$

In your method, you would build a model which maps the input features (ad type, customer descriptors) to the output (purchase made = 0/1). You can use a model such as a logistic regression, or a decision tree (which can model the interaction effects between the ad type and the customer descriptors.) This seems to be reasonable and is one of the approaches commonly used for ad selection.

A few other options based on customer similarity:

  • Near-neighbour based approach: Based on the customer descriptors, identify similar neighbours of the current customer. Compute the probability of conversion for each ad type for all the neighbours put together, and pick the ad type which has the highest probability of conversion.

  • Cluster based approach: Form clusters of customers based on the customer descriptors. Map the current customer into one of the clusters, and pick the ad type which maximizes conversion probability for that cluster.

With respect to designing a system of ad selection using such a model, it is also important for the system to explore new regions of the space, so some small randomization of predictions will help here.

|improve this answer|||||
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.