Resumen

CUEVAS SOTO, Ing. Victor Manuel; ALVARES IRIARTE, Lic. Susana; AZCONA ROMERO, Lic. Mileydis  y  RODRIGUEZ ROGERT, Msc. A. Israel. Predictive power of the Support Vector Machine. An application to the financial planning. Rev cuba cienc informat [online]. 2019, vol.13, n.3, pp. 59-75. ISSN 2227-1899.

In recent years, the use of non-linear models for prediction and classification through algorithms and advanced computational techniques (Machine Learning) have emerged as an efficient alternative for modeling economic processes. The present work was developed with the objective of building a model to forecast the projection of revenues in the Maintenance Company to Power Plants (EMCE). The modeling was carried out through the Support Vector Machine (SVM) algorithm, obtaining 95.8% of hits with the RBF kernel function. A graphical tool (graph of prognostic projections) is proposed for the interpretation of forecasts about projections of variables of an economic nature.

Palabras clave : Forecasting; Artificial Intelligence; Time Series; Support Vector Machine; Machine Learning.

        · resumen en Español     · texto en Español     · Español ( pdf )