Market Forecasting
Jump to navigation
Jump to search
What is Forecasting
 Forecasting is the process of making statements about events whose actual outcomes have not yet been observed.
 Usually related to estimation for some variable of interest at some specified future date
 Prediction is a similar, but more general term
What forecast is not
 Target
 a description of where we think we are heading, based on current assumptions
 Plan
 a set of future actions designed to reach an objective
 Budget
 a sum of money allocated to an activity or action to which an organization has committed itself
Prediction
 A prediction is a statement about the way things will happen in the future, often but not always based on experience or knowledge
 Prediction may be a statement that some outcome is expected, while a forecast may cover a range of possible outcomes
Two kind of Forecasting Models
 Momentum Forecasting Models
 We can predict, but our action will not change the assumptions of the forecast
 Usually mathematical or statistical models
 Interventions Forecasting Models
 We try to asses the future in order to make decisions which in turn can usually prevent the forecast to realize
 Mostly Judgemental forecast
 There is a feedback, i.e. the forecast itself changes the future (i.e. if you don’t change the course, you will hit an iceberg)
Business Point of View
 Decisionmaking lead time
 time between taking a decision to do something and the impact being manifested
 Forecast horizon
 period of time in the future covered by a forecast
What is a Model
 A model is a simplified representation of the world.
 Complex models are not usually "better"
Models
 Mathematical
 e.g. Revenue = Volume * Price
 If we increase speed from 100km/hour to 200km/hour for the train, the travel time will be reduced by 50%
 Statistical
 Regression, Neural Networks, etc...
 People who study 30 min more pay date, with 95% confidence level, achieve around 20% better results on average
 Judgemental (gut feeling)
 e.g. "I think the recession will last 2 years longer"
 e.g. "The inflation will be around 2% next year"
Assumptions>Model>Output
TODO: Move Pictures from slide 9 (market_forecasting.odp)
Risk and Uncertainty
 Risk
 any deviation from a central forecast where the probability of occurrence can be estimated with a degree of confidence
 Uncertainty
 any possible deviation from a central forecast where the probability of occurrence cannot be estimated with a degree of confidence
Central vs Range Forecast
 Central forecast
 the "single point" forecast
 Range forecast
 the estimated range of possible outcomes
What to forecast
Important Assumption
The future will look like the past (no discontinuity happened!)
Correlation and Regression
 Correlation
 tells us whether we can predict the value of one variable if we know other variable (for example, if we know the number of hours studied, we can predict the exam results)
 Correlation tells us only about the strength and the direction
 R = 0  no correlation, we cannot predict anything
 R < 0  the more we study the less chance for passing an exam
 R > 0  the more we study the more chance for passing an exam
 The closer R is to 1 the more certain our prediction is
 Regression model allow us to quantify the prediction
Regression model
 relationship between a dependent variable and one or more independent variables.
E(Y  X) = f(X, β)
 The unknown parameters denoted as β; this may be a scalar or a vector.
 The independent variables, X
 AKA: covariate, explanatory, predictor, control variable
 The dependent variable, Y.
Regression Assumptions
 The sample is representative of the population for the inference prediction
 The error is a random variable with a mean of zero conditional on the explanatory variables.
 The independent variables are measured with no error.
 The predictors are linearly independent, i.e. it is not possible to express any predictor as a linear combination of the others. See Multicollinearity.
 The errors are uncorrelated
 The variance of the error is constant across observations (homoscedasticity). If not, weighted least squares or other methods might instead be used.
Types of Regression
 Shape of the function

 Linear
 Nonlinear
 Number of predictors

 Simple (one predictor)
 General Multiple Regression
Ordinary Least Square
 Finds the line which minimizes squared distances scores from the line
 Uses calculus
Exercise
CorrelationAndRegression.xls in repository
Moving Average
 The moving average is the plot line connecting all the (fixed) averages
 Moving average smooth the price data to form a trend following indicator
 They do not predict price direction, but rather define the current direction with a lag
 Types

 Simple Moving Average (SMA)
 Exponential Moving Average (EMA)
Simple Moving Average (SMA)
Weighted Moving Average (WMA)
Exponential Smoothing
Forecast Error Measures
Forecast Error Measures
Exercises
For MA(2) and ES(a=0.7) calculate:
 Tracing Signal
 Bias
 Which method has the lowest bias
 Which method has the highest bias
Forecasting Exercises  Sprite Sales
Code to paste
sp = scan("Z:/sprite.dat")
plot(sp,type="l")
spts = ts(sp,start=1991,frequency=12)
par(tck=1,lab=c(20,5,14),col="red")
plot(spts)
Forecasting ETS
fc = forecast(spts)
print(fc)
plot(fc)
plot(fc$residuals)
lines(fc$fitted)
What sales of Sprite in Jan 1997 are going to be? (give range and point estimation)
ARIMA (auto)
ar = auto.arima(spts)
fc = forecast(ar)
plot(fc)
Quiz  Question 1
What is the advantage of Nperiod moving averages method over simple mean forecasting method?
 (a) easy to use
 (b) not sensitive to a shift in recent data
 +(c) needs space to maintain only the "N" most recent periods of data points
 (d) none of the above
Quiz  Question 2
Question 2. The demand for certain items is given for 6 consecutive months as follows: 45, 50, 42, 40, 48, 52. What is the forecast demand for 7th month if three period moving average is applied?
 (a) 46.2
 +(b) 46.66
 (c) 46.4
 (d) 50
Judgemental Methods
 Surveys
 Delphi method
 Scenario building
 Technology forecasting
 Forecast by analogy
Surveys
 You ask representative group of people about their opinion about the probable outcome
 Can be combined with proper statistical analysis (notably hypothesis testing like "is the people prediction was by pure chance or is significant")
Delphi Method
 Structured communication technique, originally developed as a systematic, interactive forecasting method which relies on a panel of experts.
 Usually experts answer questionnaires in two or more rounds
 After each round, a facilitator provides an anonymous summary of the experts’ forecasts from the previous round as well as the reasons they provided for their judgements
 Thus, experts are encouraged to revise their earlier answers in light of the replies of other members of their panel.
 It is believed that during this process the range of the answers will decrease and the group will converge towards the "correct" answer.
 The process is stopped after a predefined stop criterion e.g.:
 number of rounds
 achievement of consensus
 stability of results
 the mean or median scores of the final rounds determine the results
 Also known as Planning Poker in Scrum (except anonymity)
Exercise
 What will be the US GBP growth in the next year?
Steps
 allow each delegate to write down their estimation with explanation
 make the files public (anonymity)
 got with the second round
Scenario Building
 Scenario is a set of parameters of the model (e.g. inflation, GDP, etc...)
 Usually judgementally estimated and optionally followed by risk
 Good example: http://en.wikipedia.org/wiki/Beyond_the_Limits
Scenario Example
 UK GBP growth
 growth (5%)
 slow growth (1%)
 double dip recession (3%)
Combining Models
 Usually we use all models (Judgemental + Statistical + Mathematical)
 For example, we want to predict the revenue, we have price and volume
 price * volume (mathematical model)
 finding trend and analysis of seasonality (statistical)
 scenario for growth  trend slope = 0, slope = 0.2, slope = 0.5
Exercise
 Using the Spectrum Analysis example, build 3 scenarios (optimistic, most probably i.e. trend doesn't change, pessimistic) and try to estimate the revenue of the company in the year 2004
 What about the risk and forecast range? Assume 95% of confidence level for the revenue.
Technology Forecasting
 We can know surprisingly accurately how the future technology will look like
 Moors Law (number transistors double very 2 years)
 Battery capacity/weight ratio law (doubling roughly every 20 years)
 Technology forecasting doesn't count for discontinuities and limits which have to assessed separately
Exercise
 How much petrol will a car use per 100km in next 10 years?
 How much electricity a washing machine will use in the next 10 years?
 What will be average usage of water for dish washers in the next 10 years?
Forecast by Analogy
 Forecast by analogy method assumes that two different kinds of phenomena shares the same model of behaviour.
 For example, one way to predict the sales of a new product is to choose an existing product which "looks like" the new product in terms of the expected demand pattern for sales of the product.
 "Used with care, an analogy is a form of scientific model that can be used to analyze and explain the behavior of other phenomena."
Exercises
How do you you think prices for space travel will behave in the future? What analogy would you use? What about:
 literacy rate in India
 Birth rate in Ethiopia?
 Quality of Chinese goods?
Time Series
 data consist of a systematic pattern (usually a set of identifiable components) and random noise (error)
 can be described in terms of two basic classes of components: trend and seasonality
Trend Analysis
 Smoothing involves some form of local averaging of data such that the nonsystematic components of individual observations cancel each other out
 The most common technique is moving average (mean or median)
 Fitting a function (usually linear)
Detrending
More: R  Time Series