Risco de crédito: uma abordagem utilizando análise discriminante, regressão logística e redes neurais artificiais

Considering the relevance of researches concerning credit risk, model diversity and the existent indicators, this thesis aimed at verifying if the Fleuriet Model contributes in discriminating Brazilian open capital companies in the analysis of credit concession. We specifically intended to i) identify the economic-financial indicators used in credit risk models; ii) identify which economic-financial indicators best discriminate companies in the analysis of credit concession; iii) assess which techniques used (discriminant analysis, logistic regression and neural networks) present the best accuracy to predict company bankruptcy. To do this, the theoretical background approached the concepts of financial analysis, which introduced themes relative to the company evaluation process; considerations on credit, risk and analysis; Fleuriet Model and its indicators, and, finally, presented the techniques for credit analysis based on discriminant analysis, logistic regression and artificial neural networks. Methodologically, the research was defined as quantitative, regarding its nature, and explanatory, regarding its type. It was developed using data derived from bibliographic and document analysis. The financial demonstrations were collected by means of the Economática ® and the BM$FBOVESPA website. The sample was comprised of 121 companies, being those 70 solvents and 51 insolvents from various sectors. In the analyses, we used 22 indicators of the Traditional Model and 13 of the Fleuriet Model, totalizing 35 indicators. The economic-financial indicators which were a part of, at least, one of the three final models were: X1 (Working Capital over Assets), X3 (NCG over Assets), X4 (NCG over Net Revenue), X8 (Type of Financial Structure), X9 (Net Thermometer), X16 (Net Equity divided by the total demandable), X17 (Asset Turnover), X20 (Net Equity Profitability), X25 (Net Margin), X28 (Debt Composition) and X31 (Net Equity over Asset). The final models presented setting values of: 90.9% (discriminant analysis); 90.9% (logistic regression) and 97.8% (neural networks). The modeling in neural networks presented higher accuracy, which was confirmed by the ROC curve. In conclusion, the indicators of the Fleuriet Model presented relevant results for the research of credit risk, especially if modeled by neural networks.

Avaliação do potencial de uso agrícola da fluorita com óxido silício (AgroSiCa), derivado da fabricação de fertilizantes fosfatados

Phosphate fertilizers are critical for crop production in tropical soils, which are known for having high phosphate-fixing capacity and aluminium saturation, as well as low pH and calcium contents. Fluorine is a component of many phosphate rocks used to make phosphate fertilizers, via a process that generates hexafluorosilicic acid (H2SiF6). While many treatment technologies have been proposed for removal of fluorine in industrial facilities, little attention has been given to a process of neutralizing H2SiF6 with calcium oxide aiming to find out an alternative and sustainable use of a by-product with a great potential for beneficial use in tropical agriculture. This study evaluated the effect of a by-product of phosphoric acid production (fluorite with silicon oxide, hereafter called AgroSiCa) in levels of phosphorus (P), calcium (Ca), silicon (Si), aluminum (Al) and fluorine (F) and some others parameters in soils as on growth of soybean and corn. Experiments were conducted in a greenhouse condition at the Federal University of Lavras (UFLA), Lavras, Minas Gerais, using different types of soils in tropical regions and different doses of AgroSiCa. The application of AgroSiCa resulted in a slight increase in soil pH and significant increases in calcium, phosphorus and silicon in the soil solution and the shoots of corn and soybeans. We also found very low levels of fluoride in all soil leachates. A significant reduction of labile aluminum levels found in all soils after the cultivation of corn and soybeans. In sum, AgroSiCa improved soil properties and contributed to better growth of both cultures. In sum, AgroSiCa improved soil properties and contributed to a better growth of both crops. Our results show that reacting H2SiF6 derived from the wet-process phosphoric acid production with calcium oxide leads to a by-product with potential for agricultural use, especially when applied in highly-weathered soils. Besides providing calcium and silicon to plants, the use of such by-product in soils with high phosphate-fixing capacity and high aluminium saturation delivers additional benefits, since fluoride and silicon can play an important role in improving soil conditions due to the formation of less plant-toxic forms of aluminium, as well as upon decreasing phosphate fixation, thus improving root development and making fertilizer-derived phosphate more available for plant growth.