I came across a (not new) discussion by my IBM colleague Jean Francois Puget published on the IBM developerworks entitled "What is the difference between SPSS and ILOG". Actually, while Jean Francois colors it in blue and discusses it within specific IBM products, he says that he is more interested to discuss the generic question about what is the right decision technology, as there are various technologies today that are labelled as decision technologies, decision management and other kind of decision oriented names.
Jean Francois makes the distinction between "single decision at a time" and "doing a group of decisions together" and asserts that for "single decision at a time" BRMS and/or predictive analytics is the right kind of technology, while for "doing a group of decisions together" optimization techniques are appropriate.
This has some truth to it, but I am not sure that it is the ultimate differentiation between these two types, so let's look at this issue. When there is a need to do a decision, there are several approaches:
- Get a person all relevant data and let this person do the decision
- Make automated decision (or recommendation)- when the way to do the decision can be codified as decision trees/decision tables/rules
- Make automated decision (or recommendation) -- when the decision needs to find the best alternative according to a quantified criteria.
For each of these cases, the data obtained can be deterministic or stochastic, existing or predicted, and there are various ways to achieve this type of data, but this is true regardless of the three cases. It seems that approach 1 does not require any decision technology - although some people call requested data that uses some kind of inference technique also a decision technology, but I think that it might be taking the term decision to non-intuitive place; approach 2 requires some kind of rule technology, and approach 3 requires some kind of optimization technology.
Now, there are cases in which single decision requires optimization. For example, a person wins the lottery and needs to get a decision where to invest the money. This is a single decision with a lot of alternatives, it requires also predictions on these alternatives, and the person has some objective function and constraints on types of investments. There are cases in which there are multiple decisions that have to be done at the same time -- for example: who should receive bonus, however the amount of bonus recipients is fixed, and the criteria are very simple, so no optimization should be done, just a lot of rules applied to all candidates to rank each of them, and then sort by the ranking. So there is selection between alternatives, but optimization is not really required. While there is some correlation between the criteria specified by Jean Francois and what I have written here, but it seems to me that the main distinction is what is the kind of decision, and the way alternatives are compared... More on this - later.