Studying the Performance of Cognitive Models in Time Series Forecasting

Ademir Batista Santos Neto; Tiago Alessandro Espindola Ferreira; Maria Conceição Moraes Batista; Paulo Renato Alves Firmino

doi:10.22456/2175-2745.96181

Authors

Ademir Batista Santos Neto Univerisdade Federal Rural de Pernambuco
Tiago Alessandro Espindola Ferreira Univerisdade Federal Rural de Pernambuco
Maria Conceição Moraes Batista Univerisdade Federal Rural de Pernambuco
Paulo Renato Alves Firmino Universidade Federal do Cariri

DOI:

https://doi.org/10.22456/2175-2745.96181

Keywords:

Cognitive Models, ARIMA Models, Elicitation of Knowledge, Time Series Forecasting

Abstract

Cognitive models have been paramount for modeling phenomena for which empirical data are unavailable, scarce, or only partially relevant. These approaches are based on methods dedicated to preparing experts and then to elicit their opinions about the variables that describe the phenomena under study. In time series forecasting exercises, elicitation processes seek to obtain accurate estimates, overcoming human heuristic biases, while being less time consuming. This paper aims to compare the performance of cognitive and mathematical time series predictors, regarding accuracy. The results are based on the comparison of predictors of the cognitive and mathematical models for several time series from the M3-Competition. From the results, one can see that cognitive models are, at least, as accurate as ARIMA models predictions.

Downloads

Download data is not yet available.

References

WICKENS, C. D. et al. Engineering psychology & hu- man performance. [S.l.]: Psychology Press, 2015.

HAN, J. A goms-based granular computing model for human-computer interaction design. In: IEEE. Service Opera- tions, Logistics, and Informatics (SOLI), 2011 IEEE Interna- tional Conference on. [S.l.], 2011. p. 243–248.

FIRMINO, P. R. A.; DROGUETT, E. L. An expert opin- ion elicitation method based on binary search and bayesian intervals. International Journal of Risk Assessment and Man- agement, Inderscience Publishers (IEL), v. 18, n. 3-4, p. 336– 362, 2015.

SANTOS, W. Barbosa dos. Probablisitic analysis of risk by Baysians networks: An application to construct multilat- eral wells. Tese (MSc dissertation) — Federal University of Pernambuco, 2005.

MCCORMACK, K. P.; BRONZO, M.; OLIVEIRA, M. P. V. A probabilistic approach to risk analysis in supply chain (in portugues). Revista Produc ̧a ̃o Online, v. 10, n. 3, p. 577– 598, 2010.

FERREIRA, R. J. et al. Strategical map for human re- sources programs: Evaluating the efficience of baysian net- works. Management and Production, SciELO Brasil, v. 17, n. 1, 2010.

O’HAGAN, A. et al. Uncertain judgements: eliciting experts’ probabilities. [S.l.]: John Wiley & Sons, 2006.

AYYUB, B. M. Elicitation of expert opinions for uncer- tainty and risks. [S.l.]: CRC press, 2001.

COOKE, R. Experts in uncertainty: opinion and subjec- tive probability in science. [S.l.]: Oxford University Press on Demand, 1991.

LEU, G.; ABBASS, H. A multi-disciplinary review of knowledge acquisition methods: From human to autonomous eliciting agents. Knowledge-Based Systems, v. 105, p. 1 – 22, 2016. Dispon ́ıvel em: ⟨http://www.sciencedirect.com/science/ article/pii/S0950705116000988⟩.

SONG, B.; JIANG, Z.; LI, X. Modeling knowledge need awareness using the problematic situations elicited from ques- tions and answers. Knowledge-Based Systems, v. 75, p. 173-183, 2015. Dispon ́ıvel em: ⟨http://www.sciencedirect.com/ science/article/pii/S0950705114004341⟩.

CLEMEN, R. T.; REILLY, T. Making hard decisions with DecisionTools. [S.l.]: Cengage Learning, 2013.

HODGE, R. et al. Eliciting engineering knowledge about reliability during design-lessons learnt from implementation.

Quality and Reliability Engineering International, Wiley On- line Library, v. 17, n. 3, p. 169–179, 2001.

GARTHWAITE, P. H.; KADANE, J. B.; O’HAGAN, A. Statistical methods for eliciting probability distributions. Journal of the American Statistical Association, Taylor & Francis, v. 100, n. 470, p. 680–701, 2005.

SHADBOLT, N. R.; SMART, P. R. Knowledge elicita- tion. Evaluation of Human Work (4th ed.). CRC Press, Boca Raton, Florida, USA, p. 163–200, 2015.

KIRCHGASSNER, G.; WOLTERS, J.; HASSLER, U.

Introduction to modern time series analysis. [S.l.]: Springer Science & Business Media, 2012.

BOX, G. E. et al. Time series analysis: forecasting and control. [S.l.]:

John Wiley & Sons, 2015.

HURVICH, C. M.; TSAI, C.-L. Regression and time series model selection in small samples. Biometrika, Oxford University Press, v. 76, n. 2, p. 297–307, 1989.

AZOFF, E. M. Neural network time series forecasting of financial markets. [S.l.]: John Wiley & Sons, Inc., 1994.

KIM, K.-j. Financial time series forecasting using sup- port vector machines. Neurocomputing, Elsevier, v. 55, n. 1-2, p. 307–319, 2003.

FERREIRA, T. A.; VASCONCELOS, G. C.; ADEODATO, P. J. A new intelligent system method- ology for time series forecasting with artificial neural networks. Neural Processing Letters, Springer, v. 28, n. 2, p. 113–129, 2008.

NETO, P. S. de M. et al. A perturbative approach for enhancing the performance of time series forecast- ing. Neural Networks, v. 88, p. 114 – 124, 2017. Dispon ́ıvel em: ⟨http://www.sciencedirect.com/science/ article/pii/S0893608017300308⟩.

KUREMOTO, T. et al. Time series forecasting using a deep belief network with restricted boltzmann machines. Neurocomputing, Elsevier, v. 137, p. 47–56, 2014.

FIRMINO, P. R. et al. Eliciting engineering judgments in human reliability assessment. In: IEEE. Reliability and Maintainability Symposium, 2006. RAMS’06. Annual. [S.l.], 2006. p. 512–519.

FORD, K. M.; ADAMS-WEBBER, J. R. Knowledge acquisition and constructivist epistemology. The psychology of expertise: Cognitive research and empirical AI, Springer- Verlag, p. 121–136, 1992.

COOKE, N. J. Varieties of knowledge elicitation tech- niques. International Journal of Human-Computer Studies, Elsevier, v. 41, n. 6, p. 801–849, 1994.

KEREN, G. Calibration and probability judgements: Conceptual and methodological issues. Acta Psychologica, Elsevier, v. 77, n. 3, p. 217–273, 1991.

BRIER, G. W. Verification of forecasts expressed in terms of probability. Monthly weather review, v. 78, n. 1, p. 1–3, 1950.

EHLERS, R. S. Times series analysis. Stathistical and Geo Infromation Laboratory. Federal University of Parana, 2007.

HYNDMAN, R. J.; ATHANASOPOULOS, G. Forecast- ing: principles and practice. [S.l.]: OTexts, 2014.

MAKRIDAKIS, S.; HIBON, M. The m3-competition: results, conclusions and implications. International journal of forecasting, Elsevier, v. 16, n. 4, p. 451–476, 2000.

O’HAGAN, A. Probabilistic uncertainty specification: Overview, elaboration techniques and their application to a mechanistic model of carbon flux. Environmental Modelling & Software, Elsevier, v. 36, p. 35–48, 2012.

KYNN, M. Designing elicitor: Software to graphically elicit expert priors for logistic regression models in ecology. Available from www.winbugs-development. org. uk, Citeseer, 2006.

JAMES, A.; CHOY, S. L.; MENGERSEN, K. Elicitator: an expert elicitation tool for regression in ecology. Environ- mental Modelling & Software, Elsevier, v. 25, n. 1, p. 129–145, 2010.

MATLAB, M. The language of technical computing. The MathWorks, Inc. http://www.mathworks. com, 2012.

SCHWARZ, G. et al. Estimating the dimension of a model. The annals of statistics, Institute of Mathematical Statistics, v. 6, n. 2, p. 461–464, 1978.

SILVA, D. A. et al. Measurement of fitness function efficiency using data envelopment analysis. Expert Systems with Applications, Elsevier, v. 41, n. 16, p. 7147–7160, 2014.

LAWRENCE, M. et al. Judgmental forecasting: A review of progress over the last 25years. International Journal of Forecasting, Elsevier, v. 22, n. 3, p. 493–518, 2006.