Search

In this paper, we examine the early predictability of the market's directional movement using intraday high‐frequency data (695,764 observations) from an stock index (Ibex 35 Index) to provide, either private or institutional investors, an early warning system based on an “early indicator” of the financial market fluctuations with an optimal combination of the two more relevant variables for this strategy, accuracy, and earliness. A novel supervised machine learning early classification technique (Artificial Intelligence) has been applied, for the first time, to the high‐frequency time series of both price and certain technical indicators.The results obtained allow us to assert that the intraday movement of the Ibex 35 can be predicted with acceptable levels of accuracy 24 min after the start of the session and to establish certain informative intraday hourly patterns. Consequently, different indicators of precision and earliness in the session are generated, obtaining that, after a certain point in the session, no gains in precision are generated., Depto. de Economía Financiera y Actuarial y Estadística, Fac. de Ciencias Económicas y Empresariales, TRUE, pub

This study aims to find out how useful managers' past general and export experience is in predicting whether young manufacturing firms become fast internationalizers. Extant literature about the role of managerial experience in determining young firms' internationalization type is scant. This paper fills this gap by providing systematic evidence on which kinds of general and export experience can be used for accurate predictions of two firm types: born globals and general fast internationalizers. Our dataset encompasses information about managerial experience of the whole population of young Estonian manufacturing firms. Based on using four different prediction methods (logistic regression, rough sets, decision tree, neural networks) and a large variety of variables reflecting managers' past experience, the results indicate that in prediction models, export experience variables are more valuable than general experience variables. Born globals can be predicted with an accuracy of at least 90% in case of all applied machine learning methods, while the precision is lower in case of general fast internationalizers. The study leads to important implications for international business theory and practice., Depto. de Economía Financiera y Actuarial y Estadística, Fac. de Ciencias Económicas y Empresariales, TRUE, pub

Purpose The purpose of this paper is to investigate whether sheltered employment centers (CEEs) which have a higher rate of professionalization of their managers have better economic returns than those that have a lower one. Design/methodology/approach A questionnaire has been drawn up for their managers. After collecting the answers, an index of professionalization classifies the CEEs with managers of high, medium and low levels of professionalism. This index is then correlated with the main financial ratios of companies. Findings The results show that companies with the highest level of managers’ professionalization, on average, have higher economic returns than companies with medium and low rates, although the difference is not very high. This study is an important contribution to academic literature, as it is the first to examine the professionalization of CEE managers. Research limitations/implications Finally, this paper is not short of limitations. The number of responses is small but there are similar studies with similar response rates. Additionally, the scarcity of responses may suggest that there is a lack of interest about the utility of professionalization by some CEEs managers because, perhaps, they do not have the necessary competences to understand its importance in management Practical implications This study has some main implications for stakeholders: first, CEEs must pay more attention to the professionalization of their management team, because professionalization can lead to meeting its goals and guaranteeing the firm’s growth. Second, training programs in skills and attitudes should be designed to strengthen these competencies. Moreover, managers of social firms should know that the establishment of strategic plans will be useful to identify new opportunities in the market. Social implications Given the important role of these social firms for the employment of people with disabilities, training programs should be promoted by government in ord, Depto. de Economía Financiera y Actuarial y Estadística, Fac. de Ciencias Económicas y Empresariales, TRUE, pub

Nowadays, employment is a challenge for people but more for disabled ones. Prior literature shows that, at a European level, there are different ways for people with disabilities to find a job, such as a quota system, sheltered workshops, supported employment, etc. In Spain, sheltered employment centres are prototypes of sheltered workshops aimed at integrating more people with disabilities into the workplace. This research project aims to give visibility to these firms and to gain an understanding of their economic and financial situation. Using the whole sample of sheltered employment centres in Spain, and their financial data from 2004 to 2016, we show which variables explain their viability. Additionally, in light of the imminent worldwide crisis due to the COVID-19 pandemic situation, we want to test the impact of the last economic crisis on the profitability of sheltered employment centres. The main contribution of this study is that the size of these companies, age, financial risk and sales growth, are determining factors for their profitability. And, the economic and financial crisis has conditioned the viability of sheltered employment centres as many firms on the market registered a decrease in their profitability in the years following the crisis but survived. This study helps to shed light on the economic and financial situation of this kind of firms as well as their social visibility., Depto. de Economía Financiera y Actuarial y Estadística, Depto. de Administración Financiera y Contabilidad, Fac. de Ciencias Económicas y Empresariales, TRUE, pub

After the financial crisis and with the greater complexity of financial reporting, stakeholders asked firms for more informative audit reports to close the audit expectation gap. In this context, the International Auditing and Assurance Standards Board (IAASB) approved a new international standard on auditor’s reports. One of the major changes is the obligation for listed companies to describe the key audit matters (KAM) in the audit report, in particular, those related to the significant financial reporting risks. This paper empirically analyses the content of the new auditor’s reports after the accounting reform recently issued in Spain and the factors that condition the KAMs disclosed by auditors. Using the sample of all Spanish listed companies, our results show that these firms mostly report on two to four KAMs and the majority of these relate to revenue recognition, impairment of goodwill and deferred tax recovery in the 2017 audit reports. Applying a multinomial linear regression, the significant variables that condition the KAMs in our sample are sector, market type, and average word count. This evidence contributes to the literature by emphasizing the importance of risks in financial reporting in extended audit reports., Tras la crisis financiera y debido a la mayor complejidad de la información financiera, los grupos de interés de las empresas solicitaban un informe de auditoría más completo para reducir el gap de expectativas de la auditoría. En este contexto, el Consejo Internacional de Normas de Auditoría y Aseguramiento (IAASB) aprobó una nueva norma internacional sobre los informes de auditoría. Uno de los principales cambios es la obligación de las empresas que cotizan en bolsa de describir en el informe de auditoría las cuestiones clave de auditoría (KAMs), en particular, las relacionadas con los riesgos significativos de la información financiera. Este artículo analiza empíricamente el contenido del nuevo informe de auditoría tras la reforma contable recientemente aprobada en España y los factores que condicionan los KAMs desglosados por el auditor. Utilizando la totalidad de la muestra de empresas españolas que cotizan en bolsa, nuestros resultados indican que estas firmas presentan en su mayoría entre dos y cuatro KAMs y que casi la totalidad incluyen el reconocimiento de ingresos, el deterioro del fondo de comercio y la recuperación de impuestos diferidos en los informes de auditoría del año 2017. Aplicando una regresión lineal multinomial, las variables significativas que condicionan los KAMs en nuestra muestra son el sector, el tipo de mercado y el número medio de palabras por KAM. Esta evidencia contribuye a la literatura al enfatizar la importancia de los riesgos sobre la información financiera en el informe ampliado de auditoría., Depto. de Economía Financiera y Actuarial y Estadística, Depto. de Administración Financiera y Contabilidad, Fac. de Ciencias Económicas y Empresariales, TRUE, pub

We investigate whether key audit matter (KAM) paragraphs disclosed in extended audit reports—paragraphs in which the auditor highlights significant risks and critical judgments of the company—contribute to assess corporate credit ratings. This assessment is a complicated and expensive process to grade the reliability of a company, and it is relevant for many stakeholders, such as issuers, investors, and creditors. Although credit rating evaluations have attracted the interest of many researchers, previous studies have mainly focused only on financial ratios. We are the first to use KAMs for credit rating modelling purposes. Applying four machine learning techniques to answer this real-world problem—C4.5 decision tree, two different rule induction classifiers (PART algorithm and Rough Set) and the logistic regression methodology—, our evidence suggests that by simply identifying the KAM topics disclosed in the report, any decision-maker can assess credit scores with 74% accuracy using the rules provided by the PART algorithm. These rules specifically indicate that KAMs on both external (such as going concern) and internal (such as company debt) aspects may contribute to explaining a company’s credit rating. The rule induction classifiers have similar predictive power. Interestingly, if we combine audit data with accounting ratios, the predictive power of our model increases to 84%, outperforming the accuracy in the existing literature., Depto. de Economía Financiera y Actuarial y Estadística, Depto. de Administración Financiera y Contabilidad, Fac. de Ciencias Económicas y Empresariales, TRUE, pub

This paper examines the ability of audit report disclosures to explain the causes of business failure. Despite incremental interest in organizational failure, much of the existing literature has used accounting ratios to foresee why firms fail. We hypothesise that the audit report can also be employed for this purpose because it provides information regarding any material uncertainty relating to events that may warn users about possible causes of business default. Using a matched sample of 808 failed and non-failed firms, our results suggest that audit report disclosures significantly explain the causes of business failure. Moreover, these findings are consistent with the results of studies that integrate both deterministic and voluntaristic perspectives into the examination of the antecedents of organizational failure, as disclosures about both external and internal factors are mentioned in the audit report and contribute to assessing default. Managers, auditors, regulators and other users may consider the audit report to be useful as a tool to anticipate business failure., Depto. de Economía Financiera y Actuarial y Estadística, Fac. de Ciencias Económicas y Empresariales, TRUE, pub

Peer-to-peer (P2P) lending demands effective and explainable credit risk models. Typical machine learning algorithms offer high prediction performance, but most of them lack explanatory power. However, this deficiency can be solved with the help of the explainability tools proposed in the last few years, such as the SHAP values. In this work, we assess the well-known logistic regression model and several machine learning algorithms for granting scoring in P2P lending. The comparison reveals that the machine learning alternative is superior in terms of not only classification performance but also explainability. More precisely, the SHAP values reveal that machine learning algorithms can reflect dispersion, nonlinearity and structural breaks in the relationships between each feature and the target variable. Our results demonstrate that is possible to have machine learning credit scoring models be both accurate and transparent. Such models provide the trust that the industry, regulators and end-users demand in P2P lending and may lead to a wider adoption of machine learning in this and other risk assessment applications where explainability is required., Depto. de Economía Financiera y Actuarial y Estadística, Depto. de Ingeniería de Software e Inteligencia Artificial (ISIA), Fac. de Ciencias Económicas y Empresariales, Fac. de Informática, TRUE, pub

The main objective of this research paper is to analyze the economic and financial situation of social enterprises through ratio analysis and show their strengths and weaknesses based on financial data. The sample consists of 118 social companies operating in the Autonomous Community of Madrid in Spain. For data analysis, economic and financial analysis has been carried out, using ratio analysis and the indicator of financial distress: the Altman Z’-score. Our findings highlight that social companies are businesses with a high level of profitability, especially for their partners. Thus, their survival, on average, is guaranteed in the long-term and their liquidity level is optimum. This study is an important contribution for the academic literature, because it carries out a comparison amongst the two different types of social firms, focusing on their economic and financial structure, diminishing the lack of empirical studies about these companies., El principal objetivo de esta investigación es analizar la situación económico- financiera de las empresas sociales a través del análisis de ratios, mostrando sus fortalezas y debilidades basándonos en la información contable. La muestra está formada por 118 empresas sociales situadas en la Comunidad Autónoma de Madrid en España. Para analizar los datos se han utilizado ratios económico-financieros y el indicador de estrés financiero, el Z’-score de Altman . Nuestros resultados destacan que las empresas sociales son negocios con una elevada rentabilidad, especialmente para sus socios. De este modo, está garantizada su supervivencia en el largo plazo y con un nivel de liquidez óptimo. Este estudio es una importante contribución para la literatura académica porque establece una comparación entre dos tipos de negocios sociales centrándonos en su estructura financiera y económica, completando la escasez de estudios empíricos sobre estas empresas., Depto. de Administración Financiera y Contabilidad, Fac. de Ciencias Económicas y Empresariales, TRUE, pub

El mecanismo financiero conocido como titulización ha sido considerado como una de las causas más importantes de la crisis financiera actual.Este procedimiento que ha sido aplicado ampliamente en el mercado americano plantea varias preguntas: ¿Ha sucedido en España también? ¿Causa los mismos riesgos a nuestro sistema financiero que al sistema americano? ¿Es necesario renunciar a su uso con el fin de contar con un sistema financiero sólido, estable y saludable?. En esta investigación expresamos la necesidad de implementar medidas de control estrictas y supervisar los mecanismos para administrar el mercado de titulización por todos los participantes involucrados. El objetivo es evitar la falta de uso de este tipo de préstamos, por lo que creemos que puede ser una herramienta útil para su uso., The financial mechanism known as securitization has been considered as one of the main causes of the present financial crisis. The term subprime includes low quality loans that have caused risk and uncertainty to the whole financial system. This procedure, which has been applied widely in the American market, raises several questions: Has it happened in Spain too? Does it cause the same risks to our financial system than to the American one? Is it necessary to give up its use in order to have a solid, stable and healthy financial system? .In this paper we express the necessity of implementing strict control measures and supervising mechanisms to manage the securitization market by all the participants involved. The objective is to avoid the lack of use of this type of loans so we think it can be a useful tool to use., Depto. de Economía Financiera y Actuarial y Estadística, Fac. de Ciencias Económicas y Empresariales, TRUE, pub

This study proposes a comprehensive model that helps improve self-comparisons and group-comparisons for customers to detect suspicious transactions related to money laundering (ML) and terrorism financing (FT) in financial systems. The self-comparison is improved by establishing a more comprehensive know your customer (KYC) policy, adding non-transactional characteristics to obtain a set of variables that can be classified into four categories: inherent, product, transactional, and geographic. The group-comparison involving the clustering process is improved by using an innovative transaction abnormality indicator, based on the variance of the variables. To illustrate the way this methodology works, random samples were extracted from the data warehouse of an important financial institution in Mexico. To train the algorithms, 26,751 and 3527 transactions and their features, involving natural and legal persons, respectively, were selected randomly from January 2020. To measure the prediction accuracy, test sets of 1000 and 600 transactions were selected randomly for natural and legal persons, respectively, from February 2020. The proposed model manages to decrease the proportion of false positives and increase accuracy when compared to the rule-based system. On reducing the false positive rate, the company’s costs for investigating suspicious customers also decrease significantly., Universidad Complutense de Madrid/Banco de Santander, Depto. de Administración Financiera y Contabilidad, Fac. de Ciencias Económicas y Empresariales, TRUE, pub

The negative impact of insolvency, especially in small and medium enterprises, informs the objective of this paper: to study the characteristics of bankrupt firms to achieve a preventive diagnosis for reorganization by means of artificial intelligence (AI) methodologies such as rough set and PART methods. The AI models obtained show not only the key variables to predict insolvency, but also their relations and the critical values. Using only five firm characteristics (sector, size, number of shareholdings, return on assets, and cash ratio), our model could reduce delays and costs, since it is able to predict which firms will undergo reorganization or liquidation before the legal procedure., Depto. de Administración Financiera y Contabilidad, Fac. de Ciencias Económicas y Empresariales, TRUE, pub

Este trabajo fue parcialmente financiado por el Ministerio de Ciencia e Innovación de España por el proyecto: ref. ECO2010-22065-C03-01., La gestión de riesgos, asociada al seguro del automóvil, es una cuestión crucial a la que se enfrentan en la actualidad tanto actuarios como profesionales del sector. Es clave seleccionar adecuadamente los factores de riesgos para asignar las tarifas a los asegurados en función del riesgo asociado. Por tanto, el objetivo de este trabajo es comprobar empíricamente la validez de la utilización de los niveles de “bonus-malus” para clasificar adecuadamente a los asegurados a través de dos modelos de ecuaciones estructurales. Los análisis sobre una muestra de 4.365 pólizas automovilísticas españolas descritas a través de 11 factores de riesgo muestran que la variable BM contribuye a mejorar la capacidad explicativa del modelo pero no de manera significativa., Risk management, associated to car insurance, is a crucial issue currently faced by both actuaries and field professionals. It is essential to adequately choose the risk factors to assign the payment rates to policyholders according to the associated risks. Therefore, the purpose of this work is to demonstrate, in an empirical way, the validity of using “bonus malus” (BM) levels to classify policyholders correctly through two models of structural equations. The analysis of a sample of 4,365 Spanish car insurance policies described through 11 risk factors shows that the variable BM contributes to improving the explaining capacity of the model, though not in a significant way., A gestão de riscos, associada com o seguro do automóvel, é uma questão crucial à qual se enfrentam, na atualidade, tanto atuários quanto profissionais do setor. É fundamental selecionar adequadamente os fatores de riscos para designar as tarifas aos segurados em função do risco associado. Portanto, o objetivo deste trabalho é comprovar empiricamente a validade da utilização dos níveis de bonus-malus (BM) para classificar adequadamente os segurados por meio de dois modelos de equações estruturais. As análises sobre uma amostra de 4.365 apólices automobilísticas espanholas descritas por meio de 11 fatores de risco mostram que a variável BM contribui para a melhoria da capacidade explicativa do modelo, mas não de maneira significativa., La gestion des risques associés à l’assurance du véhicule est une question cruciale que les actuaires comme les professionnels du secteur confrontent actuellement. Il est essentiel de bien choisir les facteurs de risque pour attribuer les tarifs aux assurés en fonction du risque associé. Par conséquent, le but de cet article est de tester empiriquement la validité de l’utilisation des niveaux de “bonus-malus” afin de classer correctement les assurés à travers deux modèles d’équations structurelles. Les analyses d’un échantillon de 4.365 polices d’assurance automobile espagnoles, décrites par 11 facteurs de risque, montrent que la variable BM contribue à améliorer le pouvoir explicatif du modèle, mais pas de manière significative., Ministerio de Ciencia e Innovación (MICINN), Depto. de Economía Financiera y Actuarial y Estadística, Fac. de Ciencias Económicas y Empresariales, TRUE, pub

The objective of this paper is to test the validity of using 'bonus-malus' (BM) levels to classify policyholders satisfactorily. In order to achieve the proposed objective and to show empirical evidence, an artificial intelligence method, Rough Set theory, has been employed. The empirical evidence shows that common risk factors employed by insurance companies are good explanatory variables for classifying car policyholders' policies. In addition, the BM level variable slightly increases the explanatory power of the a priori risks factors., Depto. de Economía Financiera y Actuarial y Estadística, Fac. de Ciencias Económicas y Empresariales, TRUE, pub

CRUE-CSIC (Acuerdos Transformativos 2022), Shell companies work in financial interaction with other companies to commit several crimes such as concealing resources of illicit origin (money laundering), tax fraud (tax evasion), corruption, bribery, and drug trafficking, among others. This interaction can be represented by a set of nodes and connections that show the multiple relationships between entities over time. The current article proposes to detect transactions related to shell companies in financial systems, using legal person attributes and incorporating self and group comparisons into dynamic social networks. The months of June 2019, September 2020, and November 2021 are taken as evaluation periods to test the proposed methodology. Our methodology performs better than the traditional rules method, yielding balanced accuracies and true positive rates above 0.9 and 0.85, respectively. The false-positive rate was also lower in the proposed model than in the rule system for most evaluation periods. The latter translates into a reduction in costs by compliance investigations., Ministerio de Ciencia e Innovación (MICINN), Depto. de Administración Financiera y Contabilidad, Depto. de Economía Financiera y Actuarial y Estadística, Fac. de Ciencias Económicas y Empresariales, TRUE, pub

Se plantean tres vías de actuación: 1) Formación de profesoras para que incorporen elementos STEM y de formación transversal; 2) Encuestas a alumnos para identificar áreas de actuación; 3) Formación de alumnas para mayor proyección en el mundo laboral.

En este mundo cambiante, digital y tecnológico entendemos que el talento femenino tiene no sólo mucho que aportar, sino que dicha aportación es esencial. De hecho, los indicadores de la Unión Europea ponen de manifiesto que los índices de participación en estudios universitarios se han invertido, y los hombres están pasando a ser minoría. En este sentido, en los países de la Unión Europea, en el año 2019, el porcentaje de mujeres graduadas en educación superior es mayor que el porcentaje de hombres graduados, excepto en Alemania y Grecia (INE, 2021).

Sheltered employment centres are social enterprises where at least 70% of their workers have disabilities. They are a way of helping people with disabilities to work in good working conditions and of allowing disadvantaged people to live a full life. However, some people criticise these businesses for being ghettos where public subsidies are used inefficiently. Our paper aims to test if this criticism is valid by analysing whether these companies provide social and economic value to society in return for public funding and are also economically sustainable over time. Using a sample of 997 Spanish sheltered employment centres, a descriptive analysis of the main variables has been carried out. Additionally, the results of a PART algorithm show the relationship between these companies and economic sustainability. Our findings corroborate that these firms are economically sustainable and, at the same time, socially sustainable. These results highlight the great work that such companies perform for society and the country’s economy., Universidad Complutense de Madrid/Banco de Santander, Depto. de Administración Financiera y Contabilidad, Depto. de Economía Financiera y Actuarial y Estadística, Fac. de Ciencias Económicas y Empresariales, TRUE, pub

El proyecto tiene como objetivo actualizar las guías docentes al nuevo marco legal europeo de los mercados financieros y nuestra asignatura, en particular. Integraremos la perspectiva de estudiantes y profesores, en el proceso de evaluación de calidad de los contenidos.

El presente trabajo busca evidenciar empíricamente los principales determinantes que influyen en la rentabilidad de las Cooperativas de ahorro y crédito (COAC) de Ecuador. Para este fin, se implementarán modelos de aprendizaje automático como el árbol de clasificación CART, el Random Forest y el Gradient Boosting Machine. Mediante el empleo de estos modelos se busca llegar al objetivo principal del trabajo que es predecir los determinantes de la rentabilidad y evaluar cuál de las metodologías empleadas es más eficiente en cuanto a la clasificación de las COAC en Ecuador en rentables o no rentables. Se ha elaborado una base de datos que cuenta con un total de 510 observaciones para el año 2020. Para el análisis se han seleccionado dos variables dependientes que son el ROE y la Rentabilidad de la cartera de microcrédito y, como variables independientes, y de acuerdo con la teoría revisada, se han utilizado ratios financieros específicos para este tipo de entidades que miden la liquidez, solvencia, calidad del crédito, eficiencia y tamaño de la entidad. El presente trabajo llegó a la conclusión que, de los modelos utilizados, el modelo de Gradient Boosting Machine es el que mejor predice la rentabilidad, tanto en el caso del ROE como para la rentabilidad de la cartera de microcrédito. Además, las variables relacionadas con el tamaño de la entidad y el crédito son las que más influyen a la hora de clasificar una entidad como rentable o no rentable., This work seeks to empirically demonstrate the main determinants that influence the profitability of savings and credit cooperatives in Ecuador. For this purpose, machine learning models will be implemented such as: Classification tree, Random Forest, and Gradient Boosting Machine through which it is sought to reach the main objective of the work, which is to predict the determinants of profitability and evaluate which of the methodologies used is more efficient regarding the classification of COACs in Ecuador as profitable or unprofitable. The analyzed database has a total of 510 observations for the year 2020. The dependent variables will be ROE and Profitability of the microcredit portfolio; As independent variables and in accordance with the revised theory, internal or specific factors of the financial institution will be used, which will be proportions that measure the liquidity, solvency, credit quality, efficiency, and size of the entity. The present work concluded that the Gradient Boosting Machine is the one that best predicts profitability. And the variables related to the size of the entity and the credit are the ones that most influence when classifying an entity as profitable or unprofitable.

Despite the number of studies on bankruptcy prediction using financial ratios, very little is known about how external audit information can contribute to anticipating financial distress. A handful of papers have shown that a combination of ratios and audit data is significant for predictive purposes, but only one recent paper provided a predictive accuracy of 80% solely by using the disclosures contained in audit reports. This study was complemented by simplifying the analysis of audit reports for prediction purposes and the same predictive accuracy was achieved. By applying three artificial intelligence techniques (PART algorithm, random forest, and support vector machine), the predictive ability of more easily extracted information from the report was examined and a practical implication suggested for each user. Simply by (1) finding the audit opinion, (2) identifying if a matter section exists, and (3) the number of comments disclosed, any user may predict a bankruptcy situation with the same accuracy as if they had scrutinized the whole report. In addition, an extended literature review is included, on previous studies on the interaction between bankruptcy prediction and the external audit information., Universidad Complutense de Madrid, Depto. de Economía Financiera y Actuarial y Estadística, Fac. de Ciencias Económicas y Empresariales, TRUE, pub