Peer-Review Record
Algorithmic Approaches to Inventory Management Optimization
Processes 2021, 9(1), 102; https://doi.org/10.3390/pr9010102
Reviewer 1:
Anonymous
Reviewer 2:
Anonymous
Processes 2021, 9(1), 102; https://doi.org/10.3390/pr9010102
Submission received: 1 December 2020
/
Revised: 29 December 2020
/
Accepted: 30 December 2020
/
Published: 6 January 2021
(This article belongs to the Special Issue Expanding the Horizons of Manufacturing: Towards Wide Integration, Smart Systems and Tools)
Round 1
Reviewer 1 Report
Please, consider the remarks inside the attached report.
Comments for author File: 
Comments.pdf
Author Response
Please, see attached file.
Author Response File: Author Response.pdf
Reviewer 2 Report
The paper discusses supply-chain models for a network of inventories, manufacturing facilities, and retailers. The models include lead times, production capacity limits and uncertain demand for a
single product in a finite-horizon discrete-time centralized system.
I have several remarks and suggestions for improvement.
- It might be more helpful for the reader to start the description of the model from the decision variables, rather than from the objective function and the constraints. The reader wonders which of the quantities are auxiliary when reading through the many pages describing the model.
- Why a time horizon of 30 is chosen; what is the time step? Why the Poisson distribution is chosen for the demand? It appears that the demand in every period is independent of what it was in the previous periods. Usually, a time-series model is a better choice for a stochastic process. Please elaborate on your choice. This choice affects the scenario tree in a decisive way. Can you be more specific as to how the scenario tree is generated and cite some literature to support that.
- If you assume that the demand follows the Poisson distribution with independent realizations in each time period, then you can certainly obtain better procedure for solving the corresponding Markov decision process. If you do not assume that distribution, then the comparison with multi-stage stochastic programming may not be very conclusive. Please elaborate.
- Generally the paper is nicely written and clear but many sentences start from a mathematical symbol, which impairs the readability. T
- he literature review is incomplete, specifically, the papers containing stochastic programming models or dynamic programming approaches (MDPs) are not properly reflected. T
- Typos: p. 1, l. 29, as well as on p. 10, l. 240 ``... the the ...''
Author Response
Please, see attached file.
Author Response File: Author Response.pdf
