Exam 2 - Chapter 9 Flashcards
___ is the process of projecting the values of one or more
variables into the future.
(he said read this over, most likely don need to study it, prob will be a multiple choice answer)
forecasting
Collaborative Planning, Forecasting and Replenishment (CPFR)
at Colgate-Palmolive
(read over this, teacher said make sure you understand cpfr)
• Colgate-Palmolive is a global consumer products company that
manufactures such products as toothpaste, laundry detergents, pet
foods, and soap, and it operates in over 200 countries. To reduce
supply chain costs, Colgate-Palmolive implemented a supply chain
planning process with its suppliers and customers to manage
promotional demand, improve forecasts, and synchronize activities
along the supply chain. These initiatives have improved on-time
order performance from 70 to 98 percent for vendor managed
inventories, reduced total inventories by 10 percent, and improved
customer order fulfillment rates to 95 percent.
Example of Collaborative Planning, Forecasting and Replenishment (CPFR)
◦for example, Walmart and Colgate will work together to forecast
The ______ _______ is the length of time on which a forecast is
based. This spans from short-range forecasts with a planning horizon
of under 3 months to long-range forecasts of 1 to 10 years.
planning horizon
Which one is more accurate Short range or Long range
Short Range
Two Basic Forecast Approaches
- Judgmental Forecast: this does not include the data
2. Statistical Forecast (Quantitative)
A _____ _______ is a set of observations measured at successive points
in time or over successive periods of time.
time series
A time series pattern may
have one or more of the following five characteristics:
- Judgmental Forecast
- Statistical Forecast (Quantitative)
- Trend
- Seasonal patterns
- Cyclical patterns
- Random variation (or noise) & Irregular (one time) variation
What is the keywords for time series?
Over a time period
Seasonal patterns
are characterized by repeatable
periods of ups and downs over
short periods of time, usually
within a year.
Cyclical patterns
are regular patterns in a data series that take place over long periods of time, usually more than a year.
Difference between seasonal pattern and cyclical pattern
◦Seasonal pattern is within a year
◦Cyclical pattern is more than a year
____ ______ (sometimes called noise) is the unexplained
deviation of a time series from a predictable pattern, such as a trend,
seasonal, or cyclical pattern. Because of these random variations,
forecasts are never 100% accurate.
( not sure if this is on exam or not)
random variation
___ ______ is a one-time variation that is explainable. For
example, a hurricane can cause a surge in demand for building
materials, food, and water.
( not sure if this is on exam or not)
Irregular variation
_________ ______ (_______) relies upon opinions and expertise
of people in developing forecasts. When no historical data is available,
only judgmental forecasting is possible.
Judgmental forecasting (Qualitative)
Delphi method
(test question definitely on the delphi method
The Delphi method consists of forecasting by expert opinion by gathering
judgments and opinions of key personnel based on their experience and
knowledge of the situation.
Another common approach to gathering data is a _____. Sample sizes are
usually much larger than with Delphi, but the cost of such surveys can be high.
survey
Statistical forecasting (Quantitative)
Statistical forecasting (Quantitative) is based on the assumption that the future will be an extrapolation of the past.
A moving average (MA) forecast
A moving average (MA) forecast is an average of the most recent “k”
observations in a time series. MA methods work best for short planning horizons
when there is no major trend, seasonal, or business cycle pattern. As the value of
“k” increases, the forecast reacts slowly to recent changes in the time series data.
Single Exponential Smoothing (SES)
Single Exponential Smoothing (SES) is a forecasting technique that uses a
weighted average of past time-series values to forecast the value of the time
series in the next period. The forecast “smoothes out” the irregular fluctuations in
the time series.
Linear Regression analysis
Linear Regression analysis is a method for building a statistical model that defines
a linear relationship between a single dependent variable and one or more
independent variables, all of which are numerical.
• Simple Linear Regression – one independent variable
• Multiple Linear Regression – more than one independent variables
Make sure you know the difference between simple and multiple linear regression
Simple Linear Regression – one independent variable
• Multiple Linear Regression – more than one independent variables
____ is best for single moving average
seasonal
Make sure you go over the math on slide 12
math question on he test
-
Forecast error (E)
Forecast error (E) is the difference between the observed value (A) of the time series and the forecast (F), i.e., Et = At – Ft.
[test question] how to explain a bias to someone
- On AVERAGE our forecast it is too low (if its positive)
* ON average our forecast it is too high (if its negative)
[test question] bias
• 1.93 units for measure
◦on average my forecast is off by 1.93 units and its little bit too low
A major problem of Bias error measure is that it
A major problem of Bias error measure is that it
ignores the sign (+/-) of
errors. For example, +9 – 9 = 0 (no error).
A major difference between MSE and MAD
A major difference between MSE and MAD is that MSE is influenced much
more by large forecasts errors than by small errors.
MAPE
MAPE is different than the other two error measures in that the measurement scale factor is eliminated by dividing the absolute error by the time-series data value. This makes the measure easier to interpret.
The selection of the best measure of forecast accuracy is not a _____
matter; indeed, forecasting experts often disagree on which measure
should be used.
simple
- How would you interpret a BIAS = 2 units?
- How would you interpret a MAD = 2 units?
- How would you interpret a MAPE = 2%?
- On average, the fx is too low.
- On average, the fx is off by 2 units.
- On average, the fx is off by 2%.