Suchergebnisse

La predicción inmediata de la actividad económica (es decir, hacer estimaciones del período actual), es conveniente porque la mayoría de las medidas tradicionales de actividad económica se realizan con rezagos sustanciales. Nuestro objetivo es predecir el ISE, un indicador de actividad económica de corto plazo en Colombia. Las entradas son los rezagos del ISE y un conjunto de datos de pagos realizados entre individuos, empresas y el gobierno central, mediante transferencias electrónicas y cheques. Bajo un enfoque de modelado predictivo, empleamos un modelo de red neuronal exógena autoregresiva no lineal. Los resultadossugieren que nuestra elección de insumos y el método predictivo, nos permiten difundir la actividad económica con una precisión razonable. Además, validamos que los datos de pagos electrónicos reducen significativamente el error de predicción en un modelo de red neuronal autoregresiva de referencia. La predicción inmediata de la actividad económica con datos de los instrumentos de pago electrónicos, no solo contribuye a la toma de decisiones de los agentes y al modelado económico, sino que también soporta nuevas vías de investigación sobre cómo utilizar dichos datos en modelos actuales. ; Economic activity nowcasting (i. e., making current-period estimates) is convenient because most traditional measures of economic activity come with substantial lags. We aim at nowcasting ise, a short-term economic activity indicator in Colombia. Inputs are the ise's lags and a dataset of payments made with electronic transfers and cheques among individuals, firms, and the central government. Under a predictive modeling approach, we employ a non-linear autoregressive exogenous neural network model. Results suggest that our choice of inputs and predictive method enable us to nowcast economic activity with fair accuracy. Also, we validate that electronic payments data significantly reduce the nowcast error of a benchmark non-linear autoregressive neural network model. Nowcasting economic activity from electronic payment instruments data not only contributes to agents' decision making and economic modeling, but also supports new research paths on how to use retail payments data for appending current models. ; A predição imediata da atividade econômica (é dizer, fazer estimações do período atual), e conveniente porque a maioria das medidas tradicionais de atividade econômica realizamse com atrasos substanciais. O nosso objetivo é predizer o ise, um indicador de atividade econômica de curto prazo na Colômbia. As entradas são os atrasos do ise e um conjunto de dados de pagamentos realizados entre indivíduos, empresas e o governo central, mediante transferências eletrônicas e cheques. Sob um enfoque de modelado preditivo, empregamos um modelo de rede neuronal exógena auto regressiva não lineal. Os resultados sugerem que nossa eleição de insumos e o método preditivo, nos permitem difundir a atividade econômica com uma precisão razoável. Além disso, validamos que os dados de pagamentos eletrônicos reduzem significativamente o erro de predição em um modelo de rede neuronal auto regressiva de referência. A predição imediata da atividade econômica com dados dos instrumentos de pagamento eletrônico, não só contribui à tomada de decisões dos agentes e ao modelado econômico, senão que também suporta novas vias de pesquisa sobre como utilizar ditos dados em modelos atuais.

La predicción inmediata de la actividad económica (es decir, hacer estimaciones del período actual), es conveniente porque la mayoría de las medidas tradicionales de actividad económica se realizan con rezagos sustanciales. Nuestro objetivo es predecir el ISE, un indicador de actividad económica de corto plazo en Colombia. Las entradas son los rezagos del ISE y un conjunto de datos de pagos realizados entre individuos, empresas y el gobierno central, mediante transferencias electrónicas y cheques. Bajo un enfoque de modelado predictivo, empleamos un modelo de red neuronal exógena autoregresiva no lineal. Los resultadossugieren que nuestra elección de insumos y el método predictivo, nos permiten difundir la actividad económica con una precisión razonable. Además, validamos que los datos de pagos electrónicos reducen significativamente el error de predicción en un modelo de red neuronal autoregresiva de referencia. La predicción inmediata de la actividad económica con datos de los instrumentos de pago electrónicos, no solo contribuye a la toma de decisiones de los agentes y al modelado económico, sino que también soporta nuevas vías de investigación sobre cómo utilizar dichos datos en modelos actuales. ; A predição imediata da atividade econômica (é dizer, fazer estimações do período atual), e conveniente porque a maioria das medidas tradicionais de atividade econômica realizamse com atrasos substanciais. O nosso objetivo é predizer o ise, um indicador de atividade econômica de curto prazo na Colômbia. As entradas são os atrasos do ise e um conjunto de dados de pagamentos realizados entre indivíduos, empresas e o governo central, mediante transferências eletrônicas e cheques. Sob um enfoque de modelado preditivo, empregamos um modelo de rede neuronal exógena auto regressiva não lineal. Os resultados sugerem que nossa eleição de insumos e o método preditivo, nos permitem difundir a atividade econômica com uma precisão razoável. Além disso, validamos que os dados de pagamentos eletrônicos reduzem significativamente o erro de predição em um modelo de rede neuronal auto regressiva de referência. A predição imediata da atividade econômica com dados dos instrumentos de pagamento eletrônico, não só contribui à tomada de decisões dos agentes e ao modelado econômico, senão que também suporta novas vias de pesquisa sobre como utilizar ditos dados em modelos atuais. ; Economic activity nowcasting (i. e., making current-period estimates) is convenient because most traditional measures of economic activity come with substantial lags. We aim at nowcasting ise, a short-term economic activity indicator in Colombia. Inputs are the ise's lags and a dataset of payments made with electronic transfers and cheques among individuals, firms, and the central government. Under a predictive modeling approach, we employ a non-linear autoregressive exogenous neural network model. Results suggest that our choice of inputs and predictive method enable us to nowcast economic activity with fair accuracy. Also, we validate that electronic payments data significantly reduce the nowcast error of a benchmark non-linear autoregressive neural network model. Nowcasting economic activity from electronic payment instruments data not only contributes to agents' decision making and economic modeling, but also supports new research paths on how to use retail payments data for appending current models.

Comunicació presentada a: 1st ACM SIGCHI International Workshop on Multimodal Interaction for Education, que va tenir lloc el 13 de novembre de 2017 a Glasgow, UK. ; Though musicians tend to agree on the importance of practicing expressivity in performance, not many tools and techniques are available for the task. A machine learning model is proposed for predicting bowing velocity during performances of violin pieces. Our aim is to provide feedback to violin students in a technology–enhanced learning setting. Predictions are generated for musical phrases in a score by matching them to melodically and rhythmically similar phrases in performances by experts and adapting the bow velocity curve measured in the experts' performance. Results show that mean error in velocity predictions and bowing direction classification accuracy outperform our baseline when reference phrases similar to the predicted ones are available. ; This work has been partly sponsored by the Spanish TIN project TIMUL (TIN 2013-48152-C2-2-R), the European Union Horizon 2020 research and innovation programme under grant agreement No. 688269 (TELMI project), and the Spanish Ministry of Economy and Competitiveness under the Maria de Maeztu Units of Excellence Programme (MDM-2015-0502).

Comunicació presentada a: 10th International Workshop on Machine Learning and Music (MML), celebrat a Barcelona (Espanya), el 6 d'octubre de 2017. ; A model is proposed for predicting expressive variations in dynamics for violin performances with the purpose of facilitating expressive performance learning by students. The model uses phrases rather than single notes as units of analysis in a lazy learning approach: each phrase in a new score is matched to phrases from expressive performances by experts, adapting the experts' transformations to render an expressive performance of the new score. In preliminary tests, the model approximates the dynamics of actual performances better than an unexpressive baseline model whenever the reference dataset contains melodies similar to those being predicted. ; This work has been partly sponsored by the Spanish TIN project TIMUL (TIN 2013-48152-C2-2-R), the European Union Horizon 2020 research and innovation programme under grant agreement No. 688269 (TELMI project), and the Spanish Ministry of Economy and Competitiveness under the Maria de Maeztu Units of Excellence Programme (MDM-2015-0502).

Presentamos una metodología general de aprendizaje automático supervisado para representar el comportamiento de pago de las instituciones financieras a partir de una base de datos de transacciones del sistema de pagos de alto valor de Colombia. La metodología utiliza una red neuronal artificial para representar los patrones de pago de instituciones financieras a través de 113 características que corresponden a su contribución a los pagos, hábitos de fondeo, momento de pagos, concentración de pagos, centralidad en la red de pagos, e impacto sistémico debido a la imposibilidad de pagar. Esta representación es utilizada para probar la coherencia de los patrones de pago fuera de muestra de una institución financiera con sus patrones de pago característicos. El desempeño del modelo es notable, con un error de clasificación fuera de muestra cercano a tres por ciento. El desempeño es robusto a reducciones en el número de características con base en la selección no supervisada de características. También se comprueba que la centralidad en la red de pagos y el impacto sistémico son características que efectivamente mejoran el desempeño de la metodología. Para las autoridades financieras este es un primer paso hacia la detección automatizada de anomalías en el comportamiento de las instituciones financieras como participantes en sistemas de pago. ; We present a general supervised machine learning methodology to represent the payment behavior of financial institutions starting from a database of transactions in the Colombian large-value payment system. The methodology learns a feedforward artificial neural network parameterization to represent the payment patterns through 113 features corresponding to financial institutions' contribution to payments, funding habits, payments timing, payments concentration, centrality in the payments network, and systemic impact due to failure to pay. The representation is then used to test the coherence of out-of-sample payment patterns of the same institution to its characteristic patterns. The performance is remarkable, with an out-of-sample classification error around three percent. The performance is robust to reductions in the number of features by unsupervised feature selection. Also, we test that network centrality and systemic impact features contribute to enhancing the performance of the methodology definitively. For financial authorities, this is the first step towards the automated detection of individual financial institutions' anomalous behavior in payment systems.

Background: Expression is a key skill in music performance, and one that is difficult to address in music lessons. Computational models that learn from expert performances can help providing suggestions and feedback to students. Aim: We propose and analyze an approach to modeling variations in dynamics and note onset timing for solo violin pieces with the purpose of facilitating expressive performance learning in new pieces, for which no reference performance is available. Method: The method generates phrase–level predictions based on musical score information on the assumption that expressiveness is idiomatic, and thus influenced by similar–sounding melodies. Predictions were evaluated numerically using three different datasets and against note–level machine–learning models, and also perceptually by listeners, who were presented to synthesized versions of musical excerpts, and asked to choose the most human–sounding one. Some of the presented excerpts were synthesized to reflect the variations in dynamics and timing predicted by the model, whereas others were shaped to reflect the dynamics and timing of an actual expert performance, and a third group was presented with no expressive variations. Results: surprisingly, none of the three synthesized versions was consistently selected as human–like nor preferred with statistical significance by listeners. Possible interpretations of these results include the fact that the melodies might have been impossible to interpret outside their musical context, or that expressive features that were left out of the modeling such as note articulation and vibrato are, in fact, essential to the perception of expression in violin performance. Positive feedback by some listeners toward the modeled melodies in a blind setting indicate that the modeling approach was capable of generating appropriate renditions at least for a subset of the data. Numerically, performance in phrase–level suffers a small degradation if compared to note–level, but produces predictions easier to interpret visually, thus more useful in a pedagogical setting. ; This work has been partly sponsored by the Spanish TIN project TIMUL (TIN 2013-48152-C2-2-R), the European Union Horizon 2020 research and innovation programme under grant agreement No. 688269 (TELMI project), and the Spanish Ministry of Economy and Competitiveness under the Maria de Maeztu Units of Excellence Programme (MDM-2015-0502).