This paper argues that probability forecasts convey information on the uncertainties that surround macro-economic forecasts in a straightforward manner which is preferable to other alternatives, including the use of confidence intervals. Probability forecasts obtained using a small benchmark macroeconometric model as well as a number of other alternatives are presented and evaluated using recursive forecasts generated over the period 1999q1-2001q1. Out of sample probability forecasts of inflation and output growth are also provided over the period 2001q2-2003q1, and their implications discussed in relation to the Bank of England’s inflation target and the need to avoid recessions, both as separate events and jointly. The robustness of the results to parameter and model uncertainties is also investigated by a pragmatic implementation of the Bayesian model averaging approach.

Neural network (NN) based modeling often requires trying multiple networks with different architectures and training parameters in order to achieve an acceptable model accuracy. Typically, only one of the trained networks is selected as "best" and the rest are discarded. We propose using optimal linear combinations (OLCs) of the corresponding outputs of a set of NNs as an alternative to using a single network. Modeling accuracy is measured by mean squared error (MSE) with respect to the distribution of random inputs. Optimality is defined by minimizing the MSE, with the resultant combination referred to as MSE-OLC. We formulate the MSE-OLC problem for trained NNs and derive two closed-form expressions for the optimal combination-weights. An example that illustrates significant improvement in model accuracy as a result of using MSE-OLCs of the trained networks is included. I. INTRODUCTION Constructing neural network (NN) based models often involves training a number of networks. The cr...

We study the issue of error diversity in ensembles of neural networks. In ensembles of regression estimators, the measurement of diversity can be formalised as the Bias-Variance-Covariance decomposition. In ensembles of classifiers, there is no neat theory in the literature to date. Our objective is to understand how to precisely define, measure, and create diverse errors for both cases. As a focal point we study one algorithm, Negative Correlation (NC) Learning which claimed, and showed empirical evidence, to enforce useful error diversity, creating neural network ensembles with very competitive performance on both classification and regression problems. With the lack of a solid understanding of its dynamics, we engage in a theoretical and empirical investigation. In an initial empirical stage, we demonstrate the application of an evolutionary search algorithm to locate the optimal value for λ, the configurable parameter in NC. We observe the behaviour of the optimal parameter under different ensemble architectures and datasets; we note a high degree of unpredictability, and embark on a more formal investigation. During the theoretical investigations, we find that NC succeeds due to exploiting the

Standard statistical practice ignores model uncertainty. Data analysts typically select a model from some class of models and then proceed as if the selected model had generated the data. This approach ignores the uncertainty in model selection, leading to over-con dent inferences and decisions that are more risky than one thinks they are. Bayesian model averaging (BMA) provides a coherent mechanism for accounting for this model uncertainty. Several methods for implementing BMA haverecently emerged. We discuss these methods and present anumber of examples. In these examples, BMA provides improved out-of-sample predictive performance. We also provide a catalogue of

Forecast combinations have frequently been found in empirical studies to produce better forecasts on average than methods based on the ex-ante best individual forecasting model. Moreover, simple combinations that ignore correlations between forecast errors often dominate more refined combination schemes aimed at estimating the theoretically optimal combination weights. In this chapter we analyze theoretically the factors that determine the advantages from combining forecasts (for example, the degree of correlation between forecast errors and the relative size of the individual models’ forecast error variances). Although the reasons for the success of simple combination schemes are poorly understood, we discuss several possibilities related to model misspecification, instability (non-stationarities) and estimation error in situations where thenumbersofmodelsislargerelativetothe available sample size. We discuss the role of combinations under asymmetric loss and consider combinations of point, interval and probability forecasts. Key words: Forecast combinations; pooling and trimming; shrinkage methods; model misspecification, diversification gains

Game sites on the World Wide Web draw people from around the world with specialized interests, skills, and knowledge.

This paper examines the feasibility of rule-based forecasting, a procedure that applies forecasting expertise and domain knowledge to produce forecasts according to features of the data. We developed a rule base to make annual extrapolation forecasts for economic and demographic time series. The development of the rule base drew upon protocol analyses of five experts on forecasting methods. This rule base, consisting of 99 rules, combined forecasts from four extrapolation methods (the random walk, regression, Brown's linear exponential smoothing, and Holt's exponential smoothing) according to rules using 18 features of time series. For one-year ahead ex ante forecasts of 90 annual series, the median absolute percentage error (MdAPE) for rule-based forecasting was 13 % less than that from equally-weighted combined forecasts. For six-year ahead ex ante forecasts, rule-based forecasting had a MdAPE that was 42 % less. The improvement in accuracy of the rule-based forecasts over equally-weighted combined forecasts was statistically significant. Rule-based forecasting was more accurate than equal-weights combining in situations involving significant trends, low uncertainty, stability, and good domain expertise.

Combining the predictions of a set of classifiers has been shown to be an effective way to create composite classifiers that are more accurate than any of the component classifiers. Increased accuracy has been shown in a variety of real-world applications, ranging from protein sequence identification to determining the fat content of ground meat. Despite such individual successes, the answers are not known to fundamental questions about classifier combination, such as "Can classifiers from any given model class be combined to create a composite classifier with higher accuracy?" or "Is it possible to increase the accuracy of a given classifier by combining its predictions with those of only a small number o...

Novel artificial intelligence methods are used to classify 16x16 pixel regions (obtained from Advanced Very High Resolution Radiometer (AVHRR) images) in terms of cloud type (e.g., stratus, cumulus, etc.). We previously reported that intelligent feature selection methods, combined with nearest neighbor classifiers, can dramatically improve classification accuracy on this task. Our subsequent analyses of the confusion matrices revealed that a small number of confusable classes (e.g., cirrus and cirrostratus) dominated the classification errors. We conjectured that, if the class labels in the data were re-represented so that these cloud classes are more easily distinguished, then additional accuracy gains might result. We explored this hypothesis by replacing each class label with a set of error-correcting output codes, a general technique applicable to any classification algorithm for tasks with at least three classes. Our initial results are promising; error correcting codes significa...

This paper addresses that issue