Forecasting - An art or science

Forecasting is the process of estimation in unknown situations. Prediction sounds quite similar, but is more a generic term, and usually refers to estimation of time series, cross-sectional or longitudinal data. Forecasting is commonly used in discussion of time-series data. Predicting current and future market trends using existing data and facts. In the broader sense, analysts rely on technical and fundamental statistics to predict the directions of the economy, stock market and individual securities.

Estimating or predicting future events or conditions is never going to be easy. Forecasts may be long-term or short-term. The techniques used may be quantitative (often making use of computers) or qualitative. Quantitative forecasting models may be classified into (a) causal models in which independent variables are used to forecast dependent variables, and (b) time series models, which produce forecasts by extrapolating the historical values of the variables of interest by, eg, moving averages.

Time series methods: Time series methods use historical data as the basis for estimating future outcomes.

• Moving average
• Exponential smoothing
• Extrapolation
• Linear prediction
• Trend estimation
• Growth curve

Causal / econometric methods: Some forecasting methods use the assumption that it is possible to identify the underlying factors that might influence the variable that is being forecasted. For example, sales of umbrellas might be associated with weather conditions. If the causes are understood, projections of the influencing variables can be made and used in the forecast.

• Regression analysis using linear regression or non-linear regression
• Autoregressive moving average (ARMA)
• Autoregressive integrated moving average (ARIMA)
  e.g. Box-Jenkins
• Econometrics

Judgemental methods: Judgemental forecasting methods incorporate intuitive judgements, opinions and probability estimates.

• Composite forecasts
• Surveys
• Delphi method
• Scenario building
• Technology forecasting
• Forecast by analogy

Other methods:

• Simulation
• Prediction market
• Probabilistic forecasting and Ensemble forecasting

Forecasting accuracy: The forecast error is the difference betweent the forecast value and the actual value for the corresponding period.

Measures of aggregate error:

• Mean Absolute Error (MAE)
• Mean Absolute Percentage Error (MAPE)
• Mean squared error (MSE)
• Root Mean squared error (RMSE)

Application of forecasting: Forecasting has application in many situations. A few of them are as follows:

• Weather forecasting and Metereology
• Transport planning and Transportation forecasting
• Economic forecasting
• Technology forecasting
• Earthquake prediction
• Land use forecasting
• Product forecasting