Business Forecasting Topic 1 Flashcards

1
Q

why forecast?

A
  • uncertainty in future
  • mitigate impact of uncertainty
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

poor forecasts lead to
3 consequences

A
  • too much stock
  • unnecessarily poor service
  • over or under
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Finding a forecast

A
  • underlying pattern in past data
  • not explicit
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

components of observations

A
  1. systematic element (signal)
  2. random element (noise)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

Actual value formulae

A

signal + noise

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

noise in forecasts

A
  • irregular, random events
  • filter out noise
  • isolate systematic pattern (forecast future development)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Quantitative forecasting techniques

A
  • assume of continuity (past pattern in signal = continue to future)
  1. time series extrapolation
  2. explanatory
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

assumption of continuity

A

use quantitative methods when….
- sufficient past data
- info quantified
- valid assumption of continuity

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

time series forecasts

A

univariate method
- analyse and extrapolate past pattern
- no past data (explanatory variables) - expensive
- no idea what influences variable or explaining behaviour
- no expertise to have elaborate model, not justified by extra accuracy “might” yield
- cheap and simple

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

explanatory forecasts

A

linking variable with other variables (independent & dependent variables)

  • factor explains past through relationships with other variable
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

judgmental forecasts

A
  • subjective using expertise

1- little/no relevant past data
2- forecaster knowledgable about unique event

  • most widely used
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

five ways of combining forecasts from different methods

A
  • statistical and judgment
    1. apply judgment adj to stats forecasts
    2. simple av forecast from diff methods
    3. weighted av of forcast from diff methods
    4. bayesian - judgement estimate incorporated in stats
    5. rule based - weighted av from methods used weights based on particular conditions at time of forecast
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

Basic Steps in the forecasting task

A
  1. Define the problem
  2. Gather information
  3. Exploratory data analysis
  4. Choose method
  5. Evaluate chosen forecasting methods
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Explanatory data analysis (preliminary)

A

graph variable
- consistency of patterns
- trend and seasonality
- economic cycles/outliers are present

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

Overfitting

A

model fits past data well doesn’t guarantee accurate forecasts

  • method is seeing systematic patterns in the noise
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

two ways of evaluating methods

A

fitting period = obtain model
hold out periods = tests accuracy “out of sample” “hold out”

17
Q

four ways of presenting forecasts

A
  1. Point forecast (single figure)
  2. Prediction interval (indication of confidence)
  3. Fan charts/diagram (several prediction intervals at once)
  4. Density forecasts (normal probability distribution - large sample)
18
Q

self negating forecasts

A
  • forecast deliberate to scare people into action (change world)
    e.g. forecast loss = act as stimulus = behaviour change = avoid
    e.g opinion poll based = political party win = supporters no vote = rival wins