1
$\begingroup$

I have a huge dataset with 3 variables Company_ID, Area_code, Product_ID each one of them is a categorical variable of levels 1500,50,15 respectively,where Product_ID is the product the Company_ID is using.Each company can be located in more than one area_code and can be using more than one product.Lets call this train data.

Given a combination of Company_ID, Area_code, Product_ID ,
example- comp_025, area_012, p_10 that is not present in train data,i have to predict the probability that a company Company_ID located in area Area_Code uses the product Product_ID. So that i can recommend that product to company.

I am a beginner and having difficulty in coming up with a model. Any input is highly appreciated.

Thank you.

$\endgroup$
1
$\begingroup$

Seems like Naive Bayes of e1071 package could help.

Given the model product_id ~ comp_id + area_id it will construct conditional probabilities that may reveal some pattern in your data. For specifics, however, some sample data is nescessary.

|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.