INTRODUCTION TO QAM - Important in many areas of management.

- Production/Operations Management.
MANAGEMENT SCIENCE - Supply Chain Management.
- It is a broad interdisciplinary study of problem solving - Business Analytics
and decision making in human organizations, with
strong links to management, economics, business, BUSINESS ANALYTICS
engineering, management consulting, and other - It is a data-driven approach to decision making
sciences. It uses various scientific research-based - Large amounts of data
principles, strategies, and analytical methods - Information technology is very important
including mathematical modeling, statistics and - Statistical and quantitative analysis are used to
numerical algorithms to improve an organization's analyze the data and provide useful information
ability to enact rational and accurate management
decisions by arriving at optimal or near optimal DESCRIPTIVE ANALYTICS
solutions to complex decision problems. - It is the study and consolidation of historical data

INTRODUCTION TO MANAGEMENT SCIENCE PREDICTIVE ANALYTICS

- Mathematical tools have been used for thousands of - forecasting future outcomes based on patterns in the
years. past data
- Quantitative analysis can be applied to a wide variety
of problems. PRESCRIPTIVE ANALYTICS
- Not enough to just know the mathematics of a - It is the use of optimization methods.
technique.
- Must understand the specific applicability of the
technique, its limitations, and assumptions.
- Successful use of quantitative techniques usually
results in a solution that is timely, accurate, flexible,
economical, reliable, and easy to understand and use.

WHAT IS QUANTITATIVE ANALYSIS?

- It is a scientific approach to managerial decision
making in which raw data are processed and
manipulated to produce meaningful information.

Raw Data > Quantitative Analysis > Meaningful

Information DEFINING THE PROBLEM
- You need to develop a clear and concise statement of
- QUANTITATIVE FACTORS are data that can be the problem to provide direction and meaning.
accurately calculated. 1. This may be the most important and difficult
– Different investment alternatives step.
– Interest rates 2. Go beyond symptoms and identify true causes.
– Inventory levels 3. Concentrate on only a few of the problems –
– Demand selecting the right problems is very important.
– Labor cost 4. Specific and measurable objectives may have to
be developed.
- QUALITATIVE FACTORS are more difficult to quantify
but affect the decision process DEVELOPING A MODEL
– The weather - Models are realistic, solvable, and understandable
– Government legislation mathematical representations of a situation.
– Technological breakthroughs
DIFFERENT TYPES OF MODEL
QUANTITATIVE AND QUALITATIVE FACTORS MAY HAVE - Physical Models
DIFFERENT ROLES: - Scale Models
- Decisions based on quantitative data can be - Schematic Models
automated.
- Generally quantitative analysis will aid the decision MATHEMATICAL MODEL
making process. - A set of mathematical relationships.

1|P a ge
 - Models generally contain variables and parameters – - Changes occur over time, so even successful
Controllable variables, decision variables, are implementations must be monitored to determine if
generally unknown modifications are necessary.
- How many items should be ordered for inventory? –
Parameters are known quantities that are a part of MODELING IN THE REAL WORLD
the model - Quantitative analysis models are used extensively by
- What is the cost of placing an order? real organizations to solve real problems.
- Required input data must be available - In the real world, quantitative analysis models can be
complex, expensive, and difficult to sell.
ACQUIRING INPUT DATA - Following the steps in the process is an important
- Input data must be accurate, GIGO rule is used. component of success.

Garbage in > Process > Garbage Out HOW TO DEVELOP A QUANTITATIVE ANALYSIS MODEL
- A mathematical mode of profit:
- Data may come from a variety of sources – company Profit = Revenue – Expense
reports, documents, employee interviews, direct - Revenue and Expense can be expressed in different
measurement, or statistical sampling. ways.

DEVELOPING A SOLUTION Profit = Revenue – (Fixed cost + Variable cost)

- Manipulating the model to arrive at the best (optimal)
solution. Profit = (Selling price per unit)(Number of units
sold) – [Fixed cost + (Variable costs per unit)(Number
COMMON TECHNIQUES ARE: of units sold)]
- Solving equations
- Trial and error – trying various approaches and Profit = sX – [f + vX] Profit = sX – f – vX
picking the best result
- Complete enumeration – trying all possible values Where,
- Using an algorithm – a series of repeating steps to s = selling price per unit
reach a solution v = variable cost per unit
f = fixed cost
TESTING THE SOLUTIONS X = number of units sold
- Both input data and the model should be tested for
accuracy before analysis and implementation. - The parameters of this model are f, v, and s as these
- New data can be collected to test the model. are the inputs inherent in the model.
- Results should be logical, consistent, and represent - The decision variable of interest is X
the real situation.
EXAMPLE:
ANALYZING THE RESULT
- Determine the implications of the solution: - The company buys, sells, and repairs old clocks.
– Implementing results often requires change in an - Rebuilt springs sell for $8 per unit.
organization - Fixed cost of equipment to build springs is $1,000.
– The impact of actions or changes needs to be - Variable cost for spring material is $3 per unit.
studied and understood before implementation - s=8
- Sensitivity analysis determines how much the results - f = 1,000
will change if the model or input data changes. - v=3
– Sensitive models should be very thoroughly - Number of spring sets sold = X
tested.
If sales = 0, profits
IMPLEMENTING THE RESULTS = –f
- Implementation incorporates the solution into the = –$1,000
company. If sales = 1,000, profits
- Implementation can be very difficult. = [($8)(1,000) – $1,000 – ($3)(1,000)]
- People may be resistant to changes. = $4,000
- Many quantitative analysis efforts have failed
because a good, workable solution was not properly
implemented.

2|P a ge
 - Companies are often interested in the break-even – Fitting the textbook models.
point (BEP), the BEP is the number of units sold that – Understanding the model.
will result in $0 profit. - Acquiring accurate input data
– Using accounting data.
0 = sX – f – vX, or 0 = (s – v)X – f – Validity of the data.
- Developing a solution
Solving for X, we have – Hard-to-understand mathematics.
f = (s – v)X – Only one answer is limiting
– Testing the solution
𝑓
X= – Solutions not always intuitively obvious
𝑠−𝑣
– Analyzing the results
𝐹𝑖𝑥𝑒𝑑 𝐶𝑜𝑠𝑡 – How will it affect the total organization
BEP = (𝑆𝑒𝑙𝑙𝑖𝑛𝑔 𝑝𝑟𝑖𝑐𝑒 𝑝𝑒𝑟 𝑢𝑛𝑖𝑡)−(𝑉𝑎𝑟𝑖𝑎𝑏𝑙𝑒 𝑐𝑜𝑠𝑡 𝑝𝑒𝑟 𝑢𝑛𝑖𝑡)
IMPLEMENTATION – NOT JUST THE FINAL STEP
- Lack of commitment and resistance to change
FOR THE EXAMPLE EARLIER: - Fear formal analysis processes will reduce
management’s decision-making power
1,000
BEP = (8)−(3) - Fear previous intuitive decisions exposed as
inadequate
= 200 units
- Uncomfortable with new thinking patterns
- Action-oriented managers may want “quick and
- Sales of less than 200 units of rebuilt springs will
dirty” techniques
result in a loss.
- Management support and user involvement are
- Sales of over 200 units of rebuilt springs will result in
important
a profit.
- Lack of commitment by quantitative analysts:
- Analysts should be involved with the problem and
ADVANTAGES OF MATHEMATICAL MODELING
care about the solution
1. Models can accurately represent reality.
- Analysts should work with users and take their
2. Models can help a decision maker formulate
feelings into account
problems.
3. Models can give us insight and information.
4. Models can save time and money in decision making
and problem solving.
5. A model may be the only way to solve large or
complex problems in a timely fashion.
6. A model can be used to communicate problems and
solutions to others.

MODELS CATEGORIZED BY RISK

- Mathematical models that do not involve risk or
chance are called deterministic models.
- All of the values used in the model are known with
complete certainty.
- Mathematical models that involve risk or chance are
called probabilistic models.
- Values used in the model are estimates based on
probabilities.

POSSIBLE PROBLEMS IN THE QUANTITATIVE ANALYSIS

APPROACH
- Defining the problem.
– Problems may not be easily identified.
– Conflicting viewpoints.
– Impact on other departments.
– Beginning assumption.
– Solution outdated.
- Developing a model
3|P a ge