Title: Demand Forecasting: Time Series Models Professor Stephen R. Lawrence College of Business and Administration University of Colorado Boulder, CO 80309-0419
1Demand ForecastingTime Series
ModelsProfessor Stephen R. LawrenceCollege
of Business and AdministrationUniversity of
ColoradoBoulder, CO 80309-0419
2Forecasting Horizons
- Long Term
- 5 years into the future
- RD, plant location, product planning
- Principally judgement-based
- Medium Term
- 1 season to 2 years
- Aggregate planning, capacity planning, sales
forecasts - Mixture of quantitative methods and judgement
- Short Term
- 1 day to 1 year, less than 1 season
- Demand forecasting, staffing levels, purchasing,
inventory levels - Quantitative methods
3 Short Term ForecastingNeeds and Uses
- Scheduling existing resources
- How many employees do we need and when?
- How much product should we make in anticipation
of demand? - Acquiring additional resources
- When are we going to run out of capacity?
- How many more people will we need?
- How large will our back-orders be?
- Determining what resources are needed
- What kind of machines will we require?
- Which services are growing in demand? declining?
- What kind of people should we be hiring?
4 Types of Forecasting Models
- Types of Forecasts
- Qualitative --- based on experience, judgement,
knowledge - Quantitative --- based on data, statistics
- Methods of Forecasting
- Naive Methods --- eye-balling the numbers
- Formal Methods --- systematically reduce
forecasting errors - time series models (e.g. exponential smoothing)
- causal models (e.g. regression).
- Focus here on Time Series Models
- Assumptions of Time Series Models
- There is information about the past
- This information can be quantified in the form of
data - The pattern of the past will continue into the
future.
5Forecasting Examples
- Examples from student projects
- Demand for tellers in a bank
- Traffic on major communication switch
- Demand for liquor in bar
- Demand for frozen foods in local grocery
warehouse. - Example from Industry American Hospital Supply
Corp. - 70,000 items
- 25 stocking locations
- Store 3 years of data (63 million data points)
- Update forecasts monthly
- 21 million forecast updates per year.
6Simple Moving Average
- Forecast Ft is average of n previous
observations or actuals Dt
- Note that the n past observations are equally
weighted. - Issues with moving average forecasts
- All n past observations treated equally
- Observations older than n are not included at
all - Requires that n past observations be retained
- Problem when 1000's of items are being forecast.
7Simple Moving Average
- Include n most recent observations
- Weight equally
- Ignore older observations
weight
1/n
...
1
2
n
3
today
8Moving Average
n 3
9ExampleMoving Average Forecasting
10Exponential Smoothing I
- Include all past observations
- Weight recent observations much more heavily than
very old observations
weight
Decreasing weight given to older observations
today
11Exponential Smoothing I
- Include all past observations
- Weight recent observations much more heavily than
very old observations
weight
Decreasing weight given to older observations
today
12Exponential Smoothing I
- Include all past observations
- Weight recent observations much more heavily than
very old observations
weight
Decreasing weight given to older observations
today
13Exponential Smoothing I
- Include all past observations
- Weight recent observations much more heavily than
very old observations
weight
Decreasing weight given to older observations
today
14Exponential Smoothing Concept
- Include all past observations
- Weight recent observations much more heavily than
very old observations
weight
Decreasing weight given to older observations
today
15Exponential Smoothing Math
16Exponential Smoothing Math
17Exponential Smoothing Math
- Thus, new forecast is weighted sum of old
forecast and actual demand - Notes
- Only 2 values (Dt and Ft-1 ) are required,
compared with n for moving average - Parameter a determined empirically (whatever
works best) - Rule of thumb ? lt 0.5
- Typically, ? 0.2 or ? 0.3 work well
- Forecast for k periods into future is
18Exponential Smoothing
a 0.2
19ExampleExponential Smoothing
20Complicating Factors
- Simple Exponential Smoothing works well with data
that is moving sideways (stationary) - Must be adapted for data series which exhibit a
definite trend - Must be further adapted for data series which
exhibit seasonal patterns
21Holts MethodDouble Exponential Smoothing
- What happens when there is a definite trend?
Actual
Demand
Forecast
Month
22Holts MethodDouble Exponential Smoothing
- Ideas behind smoothing with trend
- De-trend'' time-series by separating base from
trend effects - Smooth base in usual manner using ?
- Smooth trend forecasts in usual manner using ?
- Smooth the base forecast Bt
- Smooth the trend forecast Tt
- Forecast k periods into future Ftk with base and
trend
23ES with Trend
a 0.2, b 0.4
24ExampleExponential Smoothing with Trend
25Winters Method Exponential Smoothing w/ Trend
and Seasonality
- Ideas behind smoothing with trend and
seasonality - De-trend and de-seasonalizetime-series by
separating base from trend and seasonality
effects - Smooth base in usual manner using ?
- Smooth trend forecasts in usual manner using ?
- Smooth seasonality forecasts using g
- Assume m seasons in a cycle
- 12 months in a year
- 4 quarters in a month
- 3 months in a quarter
- et cetera
26Winters Method Exponential Smoothing w/ Trend
and Seasonality
- Smooth the base forecast Bt
- Smooth the trend forecast Tt
- Smooth the seasonality forecast St
27Winters Method Exponential Smoothing w/ Trend
and Seasonality
- Forecast Ft with trend and seasonality
- Smooth the trend forecast Tt
- Smooth the seasonality forecast St
28ES with Trend and Seasonality
a 0.2, b 0.4, g 0.6
29ExampleExponential Smoothing withTrend and
Seasonality
30Forecasting Performance
How good is the forecast?
- Mean Forecast Error (MFE or Bias) Measures
average deviation of forecast from actuals. - Mean Absolute Deviation (MAD) Measures average
absolute deviation of forecast from
actuals. - Mean Absolute Percentage Error (MAPE) Measures
absolute error as a percentage of the
forecast. - Standard Squared Error (MSE) Measures variance
of forecast error
31Forecasting Performance Measures
32Mean Forecast Error (MFE or Bias)
- Want MFE to be as close to zero as possible --
minimum bias - A large positive (negative) MFE means that the
forecast is undershooting (overshooting) the
actual observations - Note that zero MFE does not imply that forecasts
are perfect (no error) -- only that mean is on
target - Also called forecast BIAS
33Mean Absolute Deviation (MAD)
- Measures absolute error
- Positive and negative errors thus do not cancel
out (as with MFE) - Want MAD to be as small as possible
- No way to know if MAD error is large or small in
relation to the actual data
34Mean Absolute Percentage Error (MAPE)
- Same as MAD, except ...
- Measures deviation as a percentage of actual data
35Mean Squared Error (MSE)
- Measures squared forecast error -- error variance
- Recognizes that large errors are
disproportionately more expensive than small
errors - But is not as easily interpreted as MAD, MAPE --
not as intuitive
36Fortunately, there is software...