Introduction to Modeling

 

Introduction

 

Management Science is the study of how analytical thinking and scientific method can be used to help decision-making. The key to management science application is a mathematical model, which is a quantitative representation, or approximation, of a real problem.

 

Advantages of mathematical models:

 

Simple Waiting-Line Example

 

Descriptive model: mathematical relationships that represent a real situation

à Relationships between the inputs and outputs

 

Inputs

 

Arrival rate (customers per minute)

0.5

Service rate (customers per minute)

0.4

Maximum customers (before others go elsewhere)

5

 

 

Outputs

 

Average number in line

2.22

Average time (minutes spent) in line

6.09

Percentage of potential arrivals who don't enter

27.10%

 

Optimization model: a model that suggests desirable course of action (alternatives are presented)

 

Inputs

Decision 1

Decision 2

Decision 3

Arrival rate (customers per minute)

0.5

0.5

0.5

Service rate (customers per minute)

0.4

0.556

0.8

Maximum customers (before others go elsewhere)

5

5

5

 

 

 

 

Outputs

 

 

 

Average number in line

2.22

1.41

0.69

Average time (minutes spent) in line

6.09

3.22

1.42

Percentage of potential arrivals who don't enter

27.10%

12.60%

3.80%

 

Modeling vs. Models

 

Model: more of memorizing the detail of a particular model. For example, the simplest of all models is linear or straight line model, which describes the relationship between two variables.

 

Modeling: a process where we abstract the essence of a real problem into a model.

 

7-Step Modeling Process

 

  1. Define the problem

For example, minimizing the total costs associated with the operation of the store’s cash register

  1. Observe the System and Collect Data to estimate the value of parameters that affect the problem

  2. Formulate a Model

Analytic model can be used as an equation to relate parameters or inputs, while Simulation model can be to approximate the behavior of the actual system

  1. Verify the Model and Use the Model for Prediction

Determine whether the model developed is an accurate representation of reality

  1. Select a Suitable Alternative that best meets the objectives

  2. Present the Results of the Study to the Organization
  3. Implement and Evaluate Recommendations

Implemented system must be monitored constantly to ensure that the model meets the objectives

 

Why study Management Science

 

·        Modeling approach forces us to think logically about the relationships between variables

·        Management Science is all about the quantitative skills can be sharpened immensely

·        Spreadsheets can be used in the management science to understand the problem, as represented by the models, better. Proficient spreadsheet skill is a plus for solving large and complex problems faced by the business world

·        By studying many models and examining their solutions, one can sharpen one’s intuition considerably

 

Management Science Software

 

  1. Premium Solver: Can be used to solve problems with genetic algorithm that is different from the algorithms used by the built-in Solver
  2. Palisade Decision Tools Suite

a.   @Risk: Probability functions that can be used to perform simulation

b.   Precision Tree: Add-in that can be used to analyze decision problems with uncertainty

c.   Top Rank: What-if Analysis that determines the values in a model that has greatest impact on output.

d.   BestFit: A program that finds the distribution that best fits the data

e.   RiskView: Tool that can be used for viewing, creating and assessing probabilities graphically

f.    StatPro: Statistics add-in that enhances the statistical capabilities of Excel