Resumen de Forecasting performance of exchange rate models with heavy moving average operators

Luis F. Espinoza Audelo, Ezequiel Avilés Ochoa, E. León Castro, Fabio Raúl Blanco Mesa

• The objective of the paper is to demonstrate the effectiveness of a model which fuses econometric models and Heavy Ordered Weighted Moving Average (HOWMA) operators. The evaluation of the methodology is validated with a forecast exercise of the monthly USD / MXN parity for 2015-2017. Within the results, it is identified that the use of HOWMA operators decreases the forecast error in contrast to the time series. The limitation lies in obtaining the weights of the operator, since a change generates different results, however, this becomes its main advantage, since it allows to incorporate expectations and knowledge of market experts. The originality of the article is the presentation of a fuzzy econometric model based on information aggregation operators