I have a dataset composed by several features group by some factors (academic, personal, economic). I would like to predict the risk (high, medium, low) of dropout and its respective risk percentage. I tried to use classification models but what I need is:
Ex. 1. James Huge ==> 73% Academic - High 2. Anna Sanders ==> 45% Personal - Medium 3. Jessica Finn ==> 2% Economic - Low
¿What is the best model to achieve that?
The best model is really going to depend on your data. I'd suggest using something like the caret package in R to build and compare several models. For a three-tiered risk stratification scheme, you might want to look at multinomial logistic regression (e.g., used for three levels of behavioral risk in https://www.researchgate.net/publication/228972467_Using_Multinomial_Logistic_Models_To_Predict_Adolescent_Behavioral_Risk).
