Rule-Based Forecasting: Using Judgment in Time-Series Extrapolation

Abstract

Rule-Based Forecasting (RBF) is an expert system that uses judgment to develop and apply rules for combining extrapolations. The judgment comes from two sources, forecasting expertise and domain knowledge. Forecasting expertise is based on more than a half century of research. Domain knowledge is obtained in a structured way; one example of domain knowledge is managers= expectations about trends, which we call "causal forces. " Time series are described in terms of 28 conditions, which are used to assign weights to extrapolations. Empirical results on multiple sets of time series show that RBF produces more accurate forecasts than those from traditional extrapolation methods or equal-weights combined extrapolations. RBF is most useful when it is based on good domain knowledge, the domain knowledge is important, the series is well behaved (such that patterns can be identified), there is a strong trend in the data, and the forecast horizon is long. Under ideal conditions, the error for RBF's forecasts were one-third less than those for equal-weights combining. When these conditions are absent, RBF neither improves nor harms forecast accuracy. Some of RBF's rules can be used with traditional extrapolation procedures. In a series of studies, rules based on causal forces improved the selection of forecasting methods, the structuring of time series, and the assessment of prediction intervals. Disciplines Business | Marketing ABSTRACTRule-Based Forecasting (RBF) is an expert system that uses judgment to develop and apply rules for combining extrapolations. The judgment comes from two sources, forecasting expertise and domain knowledge. Forecasting expertise is based on more than a half century of research. Domain knowledge is obtained in a structured way; one example of domain knowledge is managers= expectations about trends, which we call "causal forces." Time series are described in terms of 28 conditions, which are used to assign weights to extrapolations. Empirical results on multiple sets of time series show that RBF produces more accurate forecasts than those from traditional extrapolation methods or equal-weights combined extrapolations. RBF is most useful when it is based on good domain knowledge, the domain knowledge is important, the series is well behaved (such that patterns can be identified), there is a strong trend in the data, and the forecast horizon is long. Under ideal conditions, the error for RBF's forecasts were one-third less than those for equal-weights combining. When these conditions are absent, RBF neither improves nor harms forecast accuracy. Some of RBF's rules can be used with traditional extrapolation procedures. In a series of studies, rules based on causal forces improved the selection of forecasting methods, the structuring of time series, and the assessment of prediction intervals.

Discrete representation strategies for foreign exchange prediction

“…These rule-based prediction methods involve two sources of knowledge; the first is forecasting expertise (e.g. quantitative extrapolations and modelling) and the second is domain knowledge (practical knowledge about causal relations within particular field) (Armstrong et al 2001). Perhaps the most popular example of the latter in finance are methods where rules are based on technical indicators.…”

“…assigning different considerations to level and trend of a time series, combining predictions of a number of models, separating models according to their forecast horizons etc. (Armstrong et al 2001). In this sense, machine learning is less restrictive compared to classical time series analysis since it does not necessarily require that a time series satisfies a specific set of assumptions.…”

Extrapolation for Time-Series and Cross-Sectional Data

“…The structured use of domain knowledge is applied in rule-based forecasting (Armstrong, Adya and Collopy 2001). I discuss statistical procedures here.…”

“…The lower level has no negative values and both the lower and upper limits are higher than those calculated using percentage errors. When a domain expert's expectation about a future trend conflicts with the trend from a traditional statistical extrapolation, we refer to the series as contrary (Armstrong, Adya and Collopy 2001). For example, if the causal force for a series is growth (domain experts expect the series to go up) and the forecasted trend (based, say, on Holt's estimate) is downward, the series is contrary.…”

“…We need empirical research to clearly identify the characteristics of extrapolation procedures and to describe the conditions under which they should be used. For example, researchers could identify time series according to the 28 conditions described by Armstrong, Adya and Collopy (2001).…”