How is IBM Watson Tradeoff Analytics any different from simple constrained decision making?

Question

I am continuously astounded by the technological genius of the IBM Watson package. The tools do things from recognizing the subjects in images to extracting the emotion in a letter, and they're amazing. And then there's Tradeoff Analytics. In their Nests demo, you select a state and then a series of constraints (price must be between W and X, square footage must be between Y and Z, there must be Insured Escrow financing available, etc.) and they rank the houses based on how well they fit your constraints.

It would seem that all Tradeoff Analytics does is run a simple query on the order of:

SELECT * FROM House WHERE price >= W AND price <= X AND square_footage >= Y
AND square_footage <= Z AND ...

Am I not understanding Tradeoff Analytics correctly? I have tremendous respect for the people over at IBM that built all of these amazing tools, but Tradeoff Analytics seems like simple constrained decision making, which appears in any Intro to Programming course as you're learning if statements. What am I missing?

Answer 1

The page you link to says they use Pareto Optimisation that tries to optimise all the parameters to come to a pareto-optimal solution - a solution or set of solutions for when you can't optimise each individual parameter, so have to settle for some sub-optimal ones.

Rather than just find anything that matches the criteria they are trying to find some sort of optimal solution(s) given the constraints. That's how it's different than simple constrained decision-making.

Note I'm basing this answer completely off of their statement:

The service uses a mathematical filtering technique called “Pareto Optimization,”...

and what I've read about Pareto problems. I have no experience with this technology or Pareto problems myself.

Answer 2

As @GuyGreer pointed out the service indeed uses Pareo Optimization which is much different than simple constraints.

For example: Say you have three houses

         Sqr Footage Price
HouseA   6000         1000K       
HouseB   9000         750K
HouseC   8000        800K

Now say your constraints are Sqr Footage > 5000 and Price < 900K then you are left with House B and House C Tradeoff Analytics will return to you only houseB. Since according to Pareto, give your objectives of Price and Footage, HouseB dominates House C as it has larger footage and is cheaper.

Obviously, this is a made up example, and in real life there are more objecitves (attributes) on which you take into account when you buy a house.

The idea with Pareto, is to find the Pareto Frontier. Tradeoff Analytics add to Pareto Optimization additional home-grown algorithms to give you more insights on the tradeoff.

Finally the service, is accompanied with a client-side widget that uses novel method for visualizing Pareto Frontiers. In its own a sophisticated problems, given that such frontier is multi-diemnsional.