Discussing the article: "Enhanced Colliding Bodies Optimization (ECBO)"

New comment
 

Check out the new article: Enhanced Colliding Bodies Optimization (ECBO).

The article discusses the Colliding Bodies Optimization (CBO) algorithm, which is based on the physics of one-dimensional collisions between bodies. The basic version of the algorithm does not include any configurable parameters, which makes it simple. Therefore, the enhanced ECBO version — supplemented with Colliding Memory and a crossover mechanism — was used as the basis for the implementation, allowing the algorithm to achieve respectable results and earn a place in the ranking table.

Colliding Bodies Optimization (CBO) is a metaheuristic optimization algorithm developed by Kaveh and Mahdavi in 2014. The algorithm draws inspiration from the physics of one-dimensional collisions between bodies, where each potential solution to the optimization problem is represented as a physical body with mass and velocity. Just as two objects in the real world exchange momentum and energy when they collide, candidate solutions in the CBO algorithm collide with one another, exchanging information about their positions in the search space and thereby guiding the search toward the optimum.

The physical metaphor for the algorithm is based on the well-known laws of conservation of momentum and energy. Consider two billiard balls: when a moving ball strikes a stationary one, both balls acquire new velocities after the collision, depending on their masses and initial velocities. At the same time, a heavier ball is harder to set in motion, while a lighter ball receives a greater impulse. It is precisely this intuition that underlies CBO: good solutions — that is, solutions with more favorable objective-function values — gain greater mass and exert a greater influence on the direction of the search, drawing poor solutions toward them.


Author: Andrey Dik

 
Andrei, good afternoon! You are testing strategies on a set of specific functions. Have you ever plotted the objective function for real-world trading optimisation problems, for example by fixing all variables except one or two at their optimised values, and leaving just one or two to visualise the graph? What do these real-world functions look like in terms of your tests?
 
And one more question, if I may. If the graph of the objective function has local extrema close to a global extremum that does not differ significantly from it in value, then in this case it does not really matter which set of parameters is chosen for practical use. Taking this idea further, it is possible that using several independent sets of parameter values, combined using a logical AND operation, would improve the reliability of the generated signals. What do you think? And is it technically feasible to implement this approach? Essentially, there is a space of solutions bounded by a surface that yields profitability above a specified level. Perhaps there is a way to improve the reliability of the signals by combining different points from this space for the purpose of mutual validation.
 
Pavel Egorov specific functions. Have you ever plotted the objective function for real-world trading optimisation problems, for example by fixing all variables except one or two at their optimised values, and leaving only one or two to visualise the graph? What do these real-world functions look like in terms of your tests?

It looks similar to Megacity
 
Pavel Egorov #:
And one more question, if I may. If the graph of the objective function has local extrema close to a global extremum that does not differ significantly from it in value, then in this case it does not make much difference which set of parameters is chosen for practical application. Taking this idea further, it is possible that using several independent sets of parameter values, combined using a logical AND operation, would improve the reliability of the generated signals. What do you think? And is it technically feasible to implement this approach? Essentially, there is a space of solutions bounded by a surface that yields profitability above a given level. Perhaps there is a way to improve the reliability of the signals by combining different points from this space for the purpose of mutual validation

These questions now relate to the following:
1. ‘Call it what you like, and it will sail that way’ – the objective function determines the surface. If you don’t like the surface, change the objective function.
2. Issues regarding the post-processing of the optimisation results obtained.

What you’re talking about makes sense, in my opinion.
 

I don’t like your work.


That’s putting it mildly.

 
lynxntech #:

I don’t like your work.

That’s fine – I’m not Angelina Jolie, so not everyone’s going to like my work.))
 
Andrey Dik #:
That’s fine – I’m not Angelina Jolie, so not everyone’s going to like my work.))
Dmitrievsky needs to be restored)
New comment