动态建模在商业管理中的应用导论

Simulation

管理系统

需积分: 9 103 浏览量更新于2024-07-31 收藏 7.94MB PDF 举报

身份认证购VIP最低享 7 折!

领优惠券(最高得80元）

“Dynamic Modeling for Business Management：An Introduction”是一本书，旨在将动态建模应用于商业管理，通过易于理解的建模技术，从基础流程逐步深入到更复杂的商业模型。本书由Bernard McGarvey和Bruce Hannon合著，他们分别来自Process Engineering Center和University of Illinois的Department of Geography。书中包含166幅插图和一张CD-ROM，提供丰富的视觉辅助材料以加深理解。系列编辑由Matthias Ruth和Bruce Hannon担任，他们分别是University of Maryland的Environmental Program和Department of Geography的成员。 “Dynamic Modeling for Business Management”探讨的核心是使用模拟技术来解决企业管理问题。模拟是一种强大的工具，它允许管理者预测和分析业务决策可能带来的结果，而无需在现实中承担风险。通过建立动态模型，企业可以更好地理解和控制复杂的过程，优化运营，以及制定更有效的策略。书中涵盖的主题可能包括： 1. **基础建模概念**：解释了动态系统的基础知识，如系统组件、输入、输出、反馈机制等，这些都是构建模型的基础。 2. **建模技术**：介绍了适用于商业环境的建模方法，如系统动力学、离散事件模拟和代理建模等，并通过实例展示如何应用这些技术。 3. **商业流程分析**：深入研究各种商业流程，如供应链管理、订单处理、销售预测等，演示如何通过动态模型改善这些流程的效率。 4. **决策支持**：讨论模型如何帮助管理者识别潜在的风险和机会，支持数据驱动的决策制定。 5. **案例研究**：通过实际商业案例，展示动态模型在解决实际问题中的应用，如库存管理、市场需求预测、成本效益分析等。 6. **软件工具**：介绍和可能提供CD-ROM上的模拟软件，帮助读者实践建模和仿真过程。 7. **数学与计算机科学的应用**：虽然强调易用性，但也会涉及数学和计算机科学的基本原理，使读者能够理解和实施复杂的模型。 8. **评估与优化**：讲解如何使用模型进行实验和测试，以确定最佳策略并持续改进业务性能。通过这本书，读者不仅可以学习到动态建模的理论，还能获得实践操作的经验，从而提升其在商业管理领域的分析和决策能力。对于商学院的学生、企业管理人员以及对商业模拟感兴趣的读者来说，这是一本极有价值的资源。

资源详情

资源推荐

Indeed, from Pythagoras through pyramidology, extreme irrationalities have often

been presented in numerical form. Astrology for centuries used the most sophisti-

cated mathematical treatments available—and is now worked out on computers:

though there is, or used to be, an English law which provided that “every person

pretending or professing to tell Fortunes, or using any subtle Craft, Means or De-

vice...shall be deemed a Rogue and Vagabond.”

—R. Conquest, History, Humanity and Truth

1.1 Introduction

Yet, we hope that our readers will see us neither as vagabonds nor rogues. We do

think that modeling is a subtle craft, an art form that is intended to help us under-

stand the future. And because of the complexity of dynamic systems, the use of

numbers is essential. The use of numbers is needed to dispel complexity, not cre-

ate it. The use of numbers forces us to be specific. Good dynamic modeling is an

art. We cannot teach you THE METHOD for this modeling, for there is none.

Modeling dynamic systems is central to our understanding of real-world phe-

nomena. We all create mental models of the world around us, dissecting our ob-

servations into cause and effect. Such mental models enable us, for example, to

cross a busy street successfully or hit a baseball. But we are not mentally

equipped to go much further. The complexities of social, economic, or ecological

systems literally force us to use aids if we want to understand much of anything

about them.

With the advent of personal computers and graphical programming, we can all

create more complex models of the phenomena in the world around us. As Heinz

Pagels noted in The Dreams of Reason in 1988, the computer modeling process is

to the mind what the telescope and the microscope are to the eye. We can model

the macroscopic results of microphenomena, and vice versa. We can simulate the

various possible futures of a dynamic process. We can begin to explain and per-

haps even to predict.

In order to deal with these phenomena, we abstract from details and attempt to

concentrate on the larger picture—a particular set of features of the real world or

Introduction to Dynamic Modeling

the structure that underlies the processes that lead to the observed outcomes.

Models are such abstractions of reality. Models force us to face the results of the

structural and dynamic assumptions we have made in our abstractions.

The process of model construction can be rather involved. However, it is possi-

ble to identify a set of general procedures that are followed frequently. These

general procedures are shown in simplified circular form in figure 1.1.

Models help us understand the dynamics of real-world processes by mimicking

with the computer the actual but simplified forces that are assumed to result in a

system’s behavior. For example, it may be assumed that the number of people mi-

grating from one country to another is directly proportional to the population liv-

ing in each country and decreases the farther these countries are apart. In a simple

version of this migration model, we may abstract away from a variety of factors

that impede or stimulate migration in addition to factors directly related to the dif-

ferent population sizes and distance. Such an abstraction may leave us with a suf-

ficiently good predictor of the known migration rates, or it may not. If it does not,

we reexamine the abstractions, reduce the assumptions, and retest the model for

its new predictions. Models help us in the organization of our thoughts, data gath-

ering, and evaluation of our knowledge about the mechanisms that lead to the sys-

tem’s change. For example, here is what Daniel Botkin said in 1977 in his Life

and Death in the Forest:

One can create a computer model of a forest ecosystem, consisting of a group of assump-

tions and information in the form of computer language commands and numbers. By oper-

ating the model the computer faithfully and faultlessly demonstrates the implications of

our assumptions and information. It forces us to see the implications, true or false, wise or

foolish, of the assumptions we have made. It is not so much that we want to believe every-

thing that the computer tells us, but that we want a tool to confront us with the implications

of what we think we know. (217)

2 1. Introduction to Dynamic Modeling

FIGURE 1.1. The basic model configuration

Some people raise philosophical questions as to why one would want to model

a system. As pointed out earlier, we all perform mental models of every dynamic

system we face. We also learn that in many cases, those mental models are inade-

quate. We can now specifically address the needs and rewards of modeling.

Throughout this book, we encounter a variety of nonlinear, time-lagged feed-

back processes, some with random disturbances that give rise to complex system

behavior. Such processes can be found in a large range of systems. The variety of

models in the companion books naturally span only a small range—but the in-

sights on which these models are based can (and should!) be used to inform the

development of models for systems that we do not cover here. The models of this

book provide a basis for the formation of analogies.

It is our intention to show you how to model, not how to use models or how to

set up a model for someone else’s use. The latter two are certainly worthwhile

activities, but we believe that the first step is learning the modeling process. In

the following section we introduce you to the computer language that is used

throughout the book. This computer language will be immensely helpful as you

develop an understanding of dynamic systems and skills for analogy formation.

Models are developed in nearly every chapter, and we have put most of the de-

veloping and final versions of these models on the CD at the back of the book.

We refer in some cases to details of the model that are only found in the CD ver-

sion.

1.2 Static, comparative static, and dynamic models

Most models fit in one of three general classes. The first type consists of static

models that represent a particular phenomenon at a point of time. For example, a

map of the United States may depict the location and size of a city or the rate of

infection with a particular disease, each in a given year. The second type, com-

parative static models, compare some phenomena at different points in time. This

is like using a series of snapshots to make inferences about the system’s path from

one point in time to another without modeling that process.

Some models describe and analyze the very processes underlying a particular

phenomenon. An example of this would be a mathematical model that describes

the demand for and supply of a good as a function of its price. If we choose a

static modeling approach, we may want to find the price under which demand and

supply are in equilibrium and investigate the properties of this equilibrium: Is the

equilibrium price a unique one or are there other prices that balance demand and

supply? Is the equilibrium stable, or are small perturbations to the system accom-

panied by a movement away from the equilibrium? Such equilibrium analysis is

widespread in economics.

Alternatively, a third type of model could be developed to show the changes in

demand and supply over time. These are dynamic models. Dynamic models try to

reflect changes in real or simulated time and take into account that the model

components are constantly evolving as a result of previous actions.

1.2 Static, comparative static, and dynamic models 3

With the arrival of easy-to-use computers and software, we can all build on the ex-

isting descriptions of a system and carry them further. The world is not a static or

comparative static process. The models treating it in that way may be misleading and

become obsolete. We can now investigate in great detail and with great precision the

system’s behavior over time, including its movement toward or away from equilib-

rium positions, rather than restricting the analysis to the equilibrium itself. “Theoret-

ical Economics will have virtually abandoned classical equilibrium theory in the

next decade; the metaphor in the short term future will be evolution, not equilib-

rium.”

To this we add our own prediction that the study of economics will evolve

over the long run into dynamic computer simulation, based to a significant extent on

game theory and experimental approaches to understanding economic processes.

Throughout the social, biological, and physical sciences, researchers examine

complex and changing interrelationships among factors in a variety of disci-

plines. What are the impacts of a change in the El Niño winds, not only on

weather patterns but also on the cost of beef in the United States? How does the

value of the Mexican peso affect the rate of oil exploration in Alaska? Every day,

scientists ask questions like these that involve dissimilar frames of reference and

even disciplines. This is why understanding the dynamics and complex interrela-

tionships among diverse systems in our increasingly complicated world is impor-

tant. A good set of questions is the start—and often the conclusion—of a good

model. Such questions help the researcher remain focused on the model without

becoming distracted by the myriad of random details that surround it.

Through computer modeling we can study processes in the real world by sketch-

ing simplified versions of the forces assumed to underlie them. As an example, you

might hypothesize that cities drew workers from farmlands as both became greater

users of technology, causing a surplus of jobs in the city and a surplus of labor in the

countryside. Another factor could be the feasibility of moving from an agricultural

area to the city. A basic version of this model might abstract away from many of the

factors that encourage or discourage such migration, in addition to those directly re-

lated to job location and the feasibility of relocation. This model could leave behind

a sufficiently good predictor of migration rates, or it might not. If the model does

not appear to be a good predictor, you can reexamine it. Did your abstractions elim-

inate any important factors? Were all your assumptions valid? You can revise your

model, based on the answers to these questions. Then you can test the revised

model for its predictions. You should now have an improved model of the system

you are studying. Even better, your understanding of that system will have grown.

You can better determine whether you asked the right questions, included all the

important factors in that system, and represented those factors properly.

Elementary to modeling is the idea that a model should be kept simple, even

simpler than the cause-and-effect relationship it studies. Add complexities to the

model only when it does not produce the real effects. Models are sketches of real

systems and are not designed to show all of the system’s many facets. Models aid

us in understanding complicated systems by simplifying them.

4 1. Introduction to Dynamic Modeling

1. Anderson 1995, 1617.

Models study cause and effect; they are causal. The modeler specifies initial

conditions and relations among these elements. The model then describes how

each condition will change in response to changes in the others. In the example of

farm workers moving to the city, workers moved in response to a lack of jobs in

the countryside. But more workers in the city would raise the demand for food in

city markets, raising the demand for farm labor. Thus, the demand for labor be-

tween the city and the country would shift, leading to migration in both directions

and changes in migration over time.

The initial conditions selected by the modeler could be actual measurements

(the number of people in a city) or estimates (how many people will be there in

four years, given normal birth rate and other specified conditions). Such estimates

are designed to reflect the process under study, not to provide precise information

about it. Therefore, the estimates could be based on real data or the reasonable

guesses of a modeler who has experience with the process. At each step in the

modeling process, documentation of the initial conditions, choice of parameters,

presumed relationships, and any other assumptions are always necessary, espe-

cially when the model is based on the modeler’s guesses.

Dynamic models have an interesting interpretation in the world of dynamical sta-

tistics. The entire dynamic model in ithink might be considered as a single regres-

sion equation, and it can be used that way in a statistical analysis for optimization of

a performance measure, such as maximizing profit. It replaces the often arbitrary

functional form of the regression equation used in statistical analysis. Thinking of

the dynamic model in this way lets one imagine that because more actual system

form and information is represented in the dynamic model, that model will produce

more accurate results. This is probably so if the same number of parameters are

used in both modeling processes. If this is not a constraint, the statistical dynamics

process known as cointegration can produce more accurate results. But one can sel-

dom determine in physical terms what aspect of the cointegration model accounted

for its accuracy; we are left with a quandary. If we wish modeling to do more than

simulate a complex process—that is, if we want a model to help us understand how

to change and improve a real-world process—we prefer to use dynamic modeling.

Statistical analysis is not involved in optimizing the performance measures to com-

plete the dynamic modeling process; it is key to finding the parameters for the in-

puts to these models. For example, we need a normal distribution to describe the

daily mean temperature to determine the heating fuel demand for an energy whole-

sale distributor. Statistical analysis is essential in determining the mean and stan-

dard deviation of these temperatures from the temperature record. Thus, using sta-

tistical analysis, we compress years of daily temperature data into a single equation,

one that is sufficient for our modeling objectives.

1.3 Model components

Model building begins, of course, with the properly focused question. Then the

modeler must decide on the boundaries of the system that contains the question,

and choose the appropriate time step and the level of detail needed. But these are

1.3 Model components 5

剩余322页未读，继续阅读

rmxjoeyjoe

粉丝: 0
资源: 5

动态建模在商业管理中的应用导论

Data Analytics with Hadoop: An Introduction for Data Scientists

Lattice Boltzmann Modeling An Introduction for Geoscientists and Engineers

Applying UML and Patterns: An Introduction to Object-Oriented Analysis and Design and Iterative Development (3rd Edition)

lbm 噪声模拟 书籍

an introduction to stochastic differential equations version微盘

topic modeling matlab

simulink经典书籍

ImportError: cannot import name 'modeling'

ImportError: cannot import name 'modeling' from 'bert' (C:\Users\wangshengke\.conda\envs\py64_name\lib\site-packages\bert\__init__.py)

powerdesigner

Detected Ceres being used as a git submodule, adding commit hook for Gerrit to: /root/package/ceres-solver/.git

c 题 生产企业原材料的订购与运输的参考文献

关于深度学习的外文文献

turbulence modeling for cfd

workbench教程课本推荐

tridet: temporal reaction detection with relative boundary modeling的引用格式

请帮我找30篇有关超导磁储能建模的IEEE外文文献

bi-vldoc: bidirectional vision-language modeling for visually-rich document

最新资源

lbm 噪声模拟书籍

ImportError: cannot import name 'modeling' from 'bert' (C:\Users\wangshengke\.conda\envs\py64_name\lib\site-packages\bert\init.py)

c 题生产企业原材料的订购与运输的参考文献