LinkedIn Xing Facebook Instagram

Natural Artificial Intelligence

Yvonne Wicke | 26. August 2019

Genetic algorithms for business optimization?

The best algorithm for optimizing behavior in a changing environment has existed for billions of years - the genes of living beings! They have allowed living creatures to survive in ice, heat and all global catastrophes.

The gene sequences represent nothing more than a program on how to build a living being. Reproduction then provides everything that is needed for optimization and adaptation.

How can we use this algorithm to optimize IT systems?

Genetic algorithms - how can nature's mechanisms be used for IT-supported optimization?

Nature uses the following procedure for optimization:

  • Building a population with different genes
  • Survival of the fittest - The fitter in the environment, the more successful in reproduction
  • Crossover: Mixing of parental genes by exchanging gene parts. This always happens when an egg and sperm cell are joined.
Natural Artificial Intelligence Child Program

  • Mutation: Random change in parts of a gene. In nature, this happens through radiation or incomplete repair of the genetic material.
Natural Artificial Intelligence Child Program

  • Development of the new generation of children with the new, modified genes

Genetic algorithms imitate this procedure.

Imagine there are

  • a program that can map a corporate environment or a corporate objective
  • and a program environment that can map the behavior in the corporate environment.

This means that we now represent a company optimization.

  1. Building a population: We randomly create programs (called "individuals" in the following) that all represent a behavior in the corporate environment.
  2. Survival of the fittest: The programs are all valid and will achieve the goal to be optimized in the company better or worse. To measure this, the programs are executed and then tested in the corporate environment.

The more successful the program, the higher the "fitness value" of the program.
The higher the fitness value, the higher the probability that an individual will "reproduce", i.e. that the program will be used for the next generation of children.

Example: Fitness value range is between 0 and 100. The probability that an individual with a fitness value of 50 will be used as a parent is then 50 times higher than an individual with a fitness value of only 1.
Now 1000 parents are being selected.

  1. Crossover: 2 parent individuals are selected. One part of the program is now cut out of each and replaced by the other. This creates 2 new programs, the "children".
  2. Mutation: With a certain probability, individual parts of the program are now randomly changed in the children.
Natural Artificial Intelligence Child Program

  1. A new generation of children has emerged and the process starts all over again in step 2.
Natural Artificial Intelligence Child Program

This approach is challenging:

  • Find a good model for representing the corporate environment.
  • Finding the right fitness function and being able to define the goal correctly.
  • Program individuals must be valid. A randomly built program must still work.
  • Finding the right parameters: How strongly does an individual with high fitness prevail over an individual with low fitness? How high is the mutation rate? How high is the population? After how many generations will the process end?

Despite the challenges, the benefits are immense. In the ever-changing corporate environment, Natural AI is used to find a set of optimized solutions. Even those that you would never have thought of, as diverse as nature itself.

TD Trusted Decisions remains a leader in this field.

Interested in the Natural AI optimization of your challenges? Please feel free to contact us at office@trusteddecisions.com

Free advice

We will be happy to help you with corporate management and data analysis.

This might also interest you.

You might also be interested in