Comparative analysis between statistical and artificial intelligence models in business failure prediction

A growing number of predicting corporate failure models has emerged since 60s. Economic and social consequences of business failure can be dramatic, thus it is not surprise that the issue has been of growing interest in academic research as well as in business context. The main purpose of this study is to compare the predictive ability of five developed models based on three statistical techniques (Discriminant Analysis, Logit and Probit) and two models based on Artificial Intelligence (Neural Networks and Rough Sets). The five models were employed to a dataset of 420 non-bankrupt firms and 125 bankrupt firms belonging to the textile and clothing industry, over the period 2003–09. Results show that all the models performed well, with an overall correct classification level higher than 90%, and a type II error always less than 2%. The type I error increases as we move away from the year prior to failure. Our models contribute to the discussion of corporate financial distress causes. Moreover it can be used to assist decisions of creditors, investors and auditors. Additionally, this research can be of great contribution to devisers of national economic policies that aim to reduce industrial unemployment.

Comparative Analysis between Statistical and Artificial Intelligence Models in Business Failure Prediction

A growing number of predicting corporate failure models has emerged since 60s. Economic and social consequences of business failure can be dramatic, thus it is not surprise that the issue has been of growing interest in academic research as well as in business context. The main purpose of this study is to compare the predictive ability of five developed models based on three statistical techniques (Discriminant Analysis, Logit and Probit) and two models based on Artificial Intelligence (Neural Networks and Rough Sets). The five models were employed to a dataset of 420 non-bankrupt firms and 125 bankrupt firms belonging to the textile and clothing industry, over the period 2003–09. Results show that all the models performed well, with an overall correct classification level higher than 90%, and a type II error always less than 2%. The type I error increases as we move away from the year prior to failure. Our models contribute to the discussion of corporate financial distress causes. Moreover it can be used to assist decisions of creditors, investors and auditors. Additionally, this research can be of great contribution to devisers of national economic policies that aim to reduce industrial unemployment.

The condensation and ordering of models of empty liquids

We consider a simple model consisting of particles with four bonding sites ("patches"), two of type A and two of type B, on the square lattice, and investigate its global phase behavior by simulations and theory. We set the interaction between B patches to zero and calculate the phase diagram as the ratio between the AB and the AA interactions, epsilon(AB)*, varies. In line with previous work, on three-dimensional off-lattice models, we show that the liquid-vapor phase diagram exhibits a re-entrant or "pinched" shape for the same range of epsilon(AB)*, suggesting that the ratio of the energy scales - and the corresponding empty fluid regime - is independent of the dimensionality of the system and of the lattice structure. In addition, the model exhibits an order-disorder transition that is ferromagnetic in the re-entrant regime. The use of low-dimensional lattice models allows the simulation of sufficiently large systems to establish the nature of the liquid-vapor critical points and to describe the structure of the liquid phase in the empty fluid regime, where the size of the "voids" increases as the temperature decreases. We have found that the liquid-vapor critical point is in the 2D Ising universality class, with a scaling region that decreases rapidly as the temperature decreases. The results of simulations and theoretical analysis suggest that the line of order-disorder transitions intersects the condensation line at a multi-critical point at zero temperature and density, for patchy particle models with a re-entrant, empty fluid, regime. (C) 2011 American Institute of Physics. [doi: 10.1063/1.3657406]

New findings on the dynamics of HIV and TB coinfection models

In this paper we study a model for HIV and TB coinfection. We consider the integer order and the fractional order versions of the model. Let α∈[0.78,1.0] be the order of the fractional derivative, then the integer order model is obtained for α=1.0. The model includes vertical transmission for HIV and treatment for both diseases. We compute the reproduction number of the integer order model and HIV and TB submodels, and the stability of the disease free equilibrium. We sketch the bifurcation diagrams of the integer order model, for variation of the average number of sexual partners per person and per unit time, and the tuberculosis transmission rate. We analyze numerical results of the fractional order model for different values of α, including α=1. The results show distinct types of transients, for variation of α. Moreover, we speculate, from observation of the numerical results, that the order of the fractional derivative may behave as a bifurcation parameter for the model. We conclude that the dynamics of the integer and the fractional order versions of the model are very rich and that together these versions may provide a better understanding of the dynamics of HIV and TB coinfection.

Landslide susceptibility assessment in Karanganyar regency - Indonesia - Comparison of knowledge-based and Data-driven Models

Dissertation submitted in partial fulfillment of the requirements for the Degree of Master of Science in Geospatial Technologies.

Subsistemas input-output y contaminación: una aplicación al sector servicions y las emisiones de CO2 en España

El análisis de subsistemas input-output nos proporciona una herramienta de gran utilidad para estudiar la estructura productiva de los diferentes sectores que componen una economía. En el presente trabajo se ha desarrollado este análisis para estudiar las emisiones de CO2 relacionadas con el conjunto de ramas productivas que conforman el sector servicios. La descomposición de la producción total del subsistema servicios nos permite obtener las emisiones de CO2 relacionadas con diferentes efectos (escala, propio, feed-back y spill over). De los resultados obtenidos, destaca el diferente papel de las distintas ramas productivas de servicios. Las actividades de transporte serían las responsables de las mayores emisiones generadas directamente en el sector. Estas actividades son demandadas por el resto de sectores de la economía en mayor grado que su propia demanda final, teniendo mayor responsabilidad la producción vendida a otros sectores que la propia demanda final. No obstante, para el resto de actividades las emisiones directas e indirectas asociadas a la demanda final son mucho más importantes, por el fuerte efecto de arrastre sobre otras ramas de la economía que ejercen las actividades de servicios. A este respecto, destacan los servicios de Comercio, Hostelería, Inmobiliarias y servicios empresariales y la Administración pública, actividades que reciben escasa atención en el diseño de políticas orientadas a reducir las emisiones, pero que tienen una responsabilidad muy destacable en el fuerte aumento de emisiones experimentado en los últimos años.

Actividad económica, consumo final de energía y requerimientos de energía primaria en Cataluña, 1990-2005. Análisis mediante el uso de los balances energéticos desde una perspectiva input-output

Este trabajo analiza la evolución de los consumos finales de energía en Cataluña durante el periodo 1990-2005. En conjunto, los consumos finales de energía crecen por encima del crecimiento del PIB en términos reales. La disponibilidad actual de datos permite una desagregación en cinco actividades: sector primario; sector industrial; sector servicios; transporte; y sector doméstico. Los aumentos relativos más importantes se dan en los sectores servicios, doméstico y transporte. Es esta última actividad (que incluye el transporte privado y comercial) la que experimenta un mayor aumento en términos absolutos, hasta llegar a representar un consumo final de energía.

Actividad económica y emisiones de CO2 derivadas del consumo de energía en Cataluña, 1990-2005. Análisis mediante el uso de los balances energéticos desde una perspectiva input-output

A lo largo del trabajo hemos analizado, tanto desde una perspectiva agregada, como posteriormente con todo el detalle posible, la evolución experimentada por estas emisiones, teniendo en cuenta las limitaciones de información . Para hacerlo se han utilizado conceptos y precisiones metodológicas ampliamente utilizadas en la literatura científica sobre el tema. Del estudio realizado en la primera parte del trabajo resulta evidente que el importante crecimiento de las emisiones en Cataluña durante el periodo considerado, de un 60.1%, muy superior a la media española (50,5%), se explica como principal factor por el aumento en el PIB per cápita, con un crecimiento del 33,35% . El crecimiento demográfico también habría contribuido de forma importante al incremento en las emisiones totales, con un aumento del 10,5% de la población; sobre todo a partir de 1999, ya que en la década de los noventa la población se mantuvo estable con pocas.

Sobre los subsistemas input-output en el análisis de emisiones contaminantes. Una aplicación a las emisiones de CH4 en Cataluña

En el presente trabajo se desarrolla un estudio de las emisiones de CH4 relacionadas con el sector agroalimentario catalán a través de un análisis alternativo, o al menos complementario, de subsistemas input-output. Una herramienta de gran utilidad para estudiar la estructura productiva de los diferentes sectores que componen una economía. La aplicación de esta técnica permite las descomposición del subsistema en distintos efectos en función de los vínculos intersectoriales existentes con el conjunto de las ramas productivas de la economía, dentro y fuera del subsistema. De los resultados obtenidos destaca la importancia de las relaciones intrasectoriales del subsistema agroalimentario, que muestra una relevante autonomía en cuanto a este tipo de emisiones respecto al resto de la economía. Esta característica orienta el tipo de políticas medioambientales a implementar con el objetivo de reducir el impacto atmosférico de dicha actividad.

Structured and unstructured continuous models for Wolbachia infections

We introduce and investigate a series of models for an infection of a diplodiploid host species by the bacterial endosymbiont Wolbachia. The continuous models are characterized by partial vertical transmission, cytoplasmic incompatibility and fitness costs associated with the infection. A particular aspect of interest is competitions between mutually incompatible strains. We further introduce an age-structured model that takes into account different fertility and mortality rates at different stages of the life cycle of the individuals. With only a few parameters, the ordinary differential equation models exhibit already interesting dynamics and can be used to predict criteria under which a strain of bacteria is able to invade a population. Interestingly, but not surprisingly, the age-structured model shows significant differences concerning the existence and stability of equilibrium solutions compared to the unstructured model.

Combining food web and species distribution models for improved community projections

The ability to model biodiversity patterns is of prime importance in this era of severe environmental crisis. Species assemblage along environmental gradient is subject to the interplay of biotic interactions in complement to abiotic environmental filtering. Accounting for complex biotic interactions for a wide array of species remains so far challenging. Here, we propose to use food web models that can infer the potential interaction links between species as a constraint in species distribution models. Using a plant-herbivore (butterfly) interaction dataset, we demonstrate that this combined approach is able to improve both species distribution and community forecasts. Most importantly, this combined approach is very useful in rendering models of more generalist species that have multiple potential interaction links, where gap in the literature may be recurrent. Our combined approach points a promising direction forward to model the spatial variation of entire species interaction networks. Our work has implications for studies of range shifting species and invasive species biology where it may be unknown how a given biota might interact with a potential invader or in future climate.

An Introduction to parametric and non-parametric models for bivariate positive insurance claim severity distributions

We present a real data set of claims amounts where costs related to damage are recorded separately from those related to medical expenses. Only claims with positive costs are considered here. Two approaches to density estimation are presented: a classical parametric and a semi-parametric method, based on transformation kernel density estimation. We explore the data set with standard univariate methods. We also propose ways to select the bandwidth and transformation parameters in the univariate case based on Bayesian methods. We indicate how to compare the results of alternative methods both looking at the shape of the overall density domain and exploring the density estimates in the right tail.

Análisis multi-región input-output (MRIO) de emisiones de gases efecto invernadero (GEI) incorporado en el comercio. Un modelo birregional aplicado a Cataluña y el resto de España

El siguiente trabajo realiza un análisis regional y sectorial para el estudio de la emisiones de gases efecto invernadero (GEI) incorporadas en el comercio entre las regiones de Cataluña y el resto de España para el año 2001, estimando así el Balance Neto en GEI incorporado. El objetivo es el desarrollo de un metodología que nos permita realizar esta estimación de forma rigurosa, con la intención de efectuar un análisis comparativo de ambas estructuras productivas territoriales, en cuanto a la intensidad de emisión y el impacto de la demanda final de las regiones consideradas. Para este propósito se utiliza el marco metodológico del análisis input-output, en particular se aplica dos tipologías de modelos: el modelo básico o single-región y el multi-región, lo que nos permite la comparabilidad entre ambos, demostrando como el modelo MRIO (multi-región input-output) es el método más apropiado para dicho propósito, permitiendo, entre otras ventajas, analizar los vínculos interregionales e intersectoriales de las regiones consideradas. La incorporación de la técnica de la integración vertical o subsistemas, nos permite un enfoque alternativo para el Balance Neto resultante, no tenemos constancia de que este enfoque haya sido utilizado con anterioridad en los análisis MRIO aplicados al estudio de los impactos medioambientales incorporados en el comercio. Tampoco la tenemos sobre la aplicación de los MRIO de forma general para estos impactos a nivel interregional de la economía española. El principal resultado obtenido nos indica que aún teniendo Cataluña un importante superávit comercial con el resto de España, hemos comprobado la existencia de un importante déficit para la primera en cuanto a la polución incorporada en este comercio.