Integration of Data Mining Classification Techniques and Ensemble Learning for Predicting the Export Potential of a Company

Abstract In this research, data mining techniques are integrated with Ensemble Learning for predicting the export potential of a company. The analysis covers the stages of measurement, evaluation and classification of companies, based on a proposal of 16 key factors of the export potential. The techniques standing out are: Synthetic Minority Oversampling Technique (Smote), K-Means Clustering, Generalized Regression Neural Network (GRNN), Feed Forward Back Propagation Neural Network (FFBPN), Support Vector Machine (SVM), Decision Tree (DT) and Naive Bayes. The neural network classifiers like GRNN and FFBPN are used for classification in MATLAB in the numeric form of data with a training and testing data ratio of 70% and 30% respectively. The accuracy of other classifiers such as SVM, DT and Naive Bayes is calculated on the nominal form of data with 80% data split. Artificial neural networks showed 85.7% of ability to discriminate and classify companies according to their competitive profile.

[1]  Hasmat Malik,et al.  Generalized Regression Neural Network Based Wind Speed Prediction Model for Western Region of India , 2016 .

[2]  David Smith.  A Neural Network Classification of Export Success in Japanese Service Firms , 2005 .

[3]  Viloria Amelec,et al.  Improvements in the Automatic Distribution Process of Finished Product for Pet Food Category in Multinational Company , 2015 .

[4]  Msc. Ing. Juan Carlos Cabarcas Reyes,et al.  Aplicación del Análisis Discriminante para Identificar Diferencias en el Perfil Productivo de las Empresas Exportadoras y no Exportadoras del Departamento del Atlántico de Colombia , 2012 .

[5]  Elena Olmedo,et al.  Caracterización no lineal y predicción no paramétrica en el IBEX35/Nonlinear Characterization and Predictions of IBEX 35 , 2007 .

[6]  Amelec Viloria,et al.  Statistical Adjustment Module Advanced Optimizer Planner and SAP Generated the Case of a Food Production Company , 2016 .

[7]  E. Uberbacher,et al.  Locating protein-coding regions in human DNA sequences by a multiple sensor-neural network approach. , 1991, Proceedings of the National Academy of Sciences of the United States of America.

[8]  Efraín De La Hoz,et al.  Metodología de Medición del Potencial Exportador de las Organizaciones Empresariales , 2016 .

[9]  Efraín De La Hoz,et al.  Aplicación de técnicas de análisis de conglomerados y redes neuronales artificiales en la evaluación del potencial exportador de una empresa , 2017 .

[10]  Amelec Viloria,et al.  Inventory Reduction in the Supply Chain of Finished Products for Multinational Companies , 2016 .

[11]  N. Ceular Villamandos,et al.  Un análisis del mercado de la vivienda a través de redes neuronales artificiales , 2001 .

[12]  Steven J. Hoff,et al.  Development and Comparison of Backpropagation and Generalized Regression Neural Network Models to Predict Diurnal and Seasonal Gas and PM10 Concentrations and Emissions from Swine Buildings , 2008 .

[13]  Amelec Viloria,et al.  Use of the Industrial Property System for New Creations in Colombia: A Departmental Analysis (2000-2016) , 2018, DMBD.

[14]  Kamran Raza,et al.  Effect Of Feature Selection, Synthetic Minority Over-sampling (SMOTE) And Under-sampling On Class imbalance Classification , 2012 .

[15]  Hortênsia Barandas,et al.  Applying Artificial Neural Networks to Evaluate Export Performance: A Relational Approach , 2009 .

[16]  Mukesh Kumar,et al.  An optimized farthest first clustering algorithm , 2013, 2013 Nirma University International Conference on Engineering (NUiCONE).

[17]  Diana Marcela Escandón Barbosa,et al.  Los determinantes de la orientación exportadora y los resultados en las pymes exportadoras en Colombia , 2014 .