Methodology of data envelopment analysis (DEA) - GLMNEt for assessment and forecasting of financial efficiency in a free trade zone - Colombia

Abstract

This research work proposes a methodology for evaluation and forecasting for companies located in the Industrial Port Zone of the city of Barranquilla, Colombia. Based on an empirical and rational analysis, supported by the concepts of technical efficiency, purely technical efficiency, additive efficiency, efficiency of scale and of mixing, as well as in the algorithm for machine learning GLMNET. Work was done with 29 companies that presented their complete financial statements for the year 2017 in the Chamber of Commerce of Barranquilla - Colombia. As a result, it was found an average technical efficiency of 72.79%, a purely technical efficiency of 82.54% and an additive efficiency of 59.45%. In addition, the projections required to make inefficient organizations achieve efficiency are contributed. From the study, it can also be observed that 11 companies were constituted as benchmarks to measure the companies of the Free Zone of the Port of Barranquilla. It is noteworthy that the algorithm GLMNET delivered a good result in the prediction of group membership of efficient and inefficient enterprises, with an accuracy of 93.1%.