The conclusion is that yes, it is.
Professor Shin Suzuki says, "The number of shipping destinations (E), number of items (I), and number of bulk items (Q) are the main factors." If there is a main factor, then there must also be sub-factors. Sub-factors are calculation rules.
The above is an example of a sub-factor.
Increasing the number of sub-factors will improve calculation accuracy.
Tera calculations have around 300 factors and are used to calculate distribution center size.
Professor Suzuki Shin also says, "EIQ and distribution center size are fractal."
If the size of a distribution center in a certain industry is like a maple leaf, changes in EIQ will make the maple leaf either larger or smaller; it will never change into a cherry blossom.
What he's saying is that if you know the EIQ, the calculation rules (sub-factors) are constant, so you can get the answer even if you don't know the calculation rules.
The concept of machine learning was born in 1950, and deep learning only began to become popular around 2010.
Professor Suzuki Arata is amazing, as he said in the early 2000s that EIQ could be used to determine the size of a distribution center.
We are currently at stage 1 above, and are working on plans for 2).
I'm looking forward to seeing how much difference there is between the distribution center size output in 3) and the size calculated in 1).
I would like to prove that the size of a distribution center can be calculated using E, I, and Q.