P501: Managing Operations &

Supply Chain

Lecture - 7
 Demand Uncertainty
 Occurs when a business or an industry is unable to accurately
predict consumer demand for its products or services.
 Can cause a number of problems, especially in managing orders
and stocking levels, with effects magnifying through the supply
chain
 It can be inherent to the business, or for external reasons.
 Seasonal fluctuations are example of inherent uncertainty.
 Businesses with a very innovative product or service will face a
great deal of demand uncertainty, simply because their
uniqueness means that there is no track record from which to
draw conclusions about demand.
 Demand Uncertainty
 Customer preference can shift rapidly and without warning because
of a new trend.
 Consumer demand can shift due to technological advances that
make familiar products obsolete.
 Demand can also be diluted by the entry of new competitors into
the industry.
 The state of the economy affects consumer demand, with a strong
economy leading to increased demand while a weak economy
depresses it.
 Natural or human-caused disasters and times of political unrest are
examples of external factors that contribute to both demand and
supply uncertainty.
 Demand Uncertainty
 As a result, it’s difficult to determine the right quantity of
supplies and goods to order.
 A business may anticipate a normal or high level of sales, only to
see the demand drop.
 Will have leftover goods that must be stored, returned or
discarded, leading to extra costs.
 If demand increases, and the company does not have a sufficient
supply of goods to sell, the result is dissatisfied customers and
loss of sales.
 Some customers may never return to the original seller.
 Demand Uncertainty
 Other than stocking of goods, it also becomes difficult to plan
appropriate staffing levels.
 Other areas of expenditure, such as equipment purchases or
facility development, may also be affected.
 Can cause tense relationships with suppliers:
 Unexpectedly high demand: company asking suppliers to quickly
produce or ship high levels of inventory right away.
 In other cases, company negotiates buyback arrangements that force
suppliers to take back excess inventory.
 Suppliers can become frustrated with constant shifting and urgent
demands.
Solution: Forecasting
 What is Forecasting?
◼ Process of predicting a future event based on historical data

◼ Educated Guessing

"Forecasting is the art of saying what will happen, and then

explaining why it didn't! "
 Importance of Forecasting
 Underlying basis of all business decisions:

✓ Production

✓ Sales

✓ Inventory

✓ Personnel

✓ Facilities
 “Planning the System” vs. “Planning the Use of the
System”
 Features of Forecasting
❑ Generally assume that the same underlying causal system of

the past will continue

❑ Is not perfect

❑ Is more accurate for grouped data than for individual items

❑ Accuracy decreases over time horizon

 Elements of a Good Forecasting
 Should be

 Timely

 Accurate, and include an estimate of error

 Reliable/Consistent

 Expressed in meaningful terms

 In written form

 Simple/easy to understand and use

 Cost effective
 Steps in Forecasting Process
1. Determine the purpose of forecasting

2. Establish a time horizon

3. Gather and analyze the appropriate data

4. Select a forecasting technique

5. Prepare the forecast

6. Monitor the forecast

 Components of True Demand
 Trend

 Seasonal element

 Cyclical element

 Irregular variation

 Random variation
Trend & Irregular variation
Seasonality
Cycle
 Approaches to Forecasting

Time Series
Quantitative
Associative
Forecasting Models

Judgment &
Qualitative
Opinion
 Qualitative Approaches

Executive
Opinion
Panel Discussion
Sales-force
Opinion

Qualitative Market Research

Approach Consumer Survey

Delphi Method
 Quantitative Forecasting

Regression
Associative Models
Analysis

Naive Method
Quantitative
Forecasting

Averaging
Time Series
Analysis
Trend

Seasonality
 Averaging

Averaging

Weighted Moving Exponential

Simple Average Moving Average
Average Smoothing
Moving Average
Weighted Moving Average
Exponential Smoothing
 Trend Analysis

Trend

Trend-Adjusted Exponential
Trend Equation
Smoothing
Trend Equation
 Seasonality Analysis

Seasonality

Deseasonalize Incorporate Seasonality

Time-Series Forecasting
Time-Series Forecasting
Time-Series Forecasting
 Forecasting Accuracy
 Error

➢ Difference between the value that occurs and the value that was
predicted for a given time period
➢ Error = Actual – Forecast

➢ e = At – Ft (t is any given time period)

➢ Positive vs. Negative Error

➢ Influence decisions in two ways:

➢ Making a choice between various forecasting techniques

➢ Evaluating the success or failure of a specific technique in use

 Forecasting Accuracy
 Three commonly used measures

➢ Mean Absolute Deviation (MAD)

➢ the average absolute error

➢ the easiest to compute

➢ weights errors linearly

 Forecasting Accuracy
 Three commonly used measures

➢ Mean Squared Error (MSE)

➢ the average of squared errors

➢ squares errors, thereby giving more weight to larger errors which

typically cause more problems

 Forecasting Accuracy
 Three commonly used measures

➢ Mean Absolute Percent Error (MAPE)

➢ the average absolute percent error

➢ used when there is a need to put errors in perspective

Thank You!