I use an expert system with forward chaining, and I would like to explain why this is better than a decision tree using very simple concepts. (in one specific situation)
I know there is a similar question in stackoverflow, but this is not the answer I'm looking for.
Here is my problem:
To manage customer relations, I use many different business rules (which call the dialogue rules) to help the client make a decision on one product. Note. Rules are added often (2 times a day).
The client answers a number of questions before receiving an answer. In business rules mixed with dialogue rules, the resulting questionnaire looks like the one generated by the optimal decision tree. Although hidden reasoning is completely different.
I would like to know what are the main arguments in favor of (or possibly against) the inference mechanism in terms of scalability, reliability, complexity and efficiency compared to the decision tree in this case.
I already have some ideas, but since I need to convince someone that I have never had enough arguments.
Thank you in advance for your ideas, and I would be glad if you could advise me on some good papers to read on this subject.