Videos de Experimentos Relacionados
Predicción de indicadores de redes financieras mediante modelos de lenguaje grandes (LLM) impulsados por series
Mini Han Wang1,2, Ying Yeung3
1The Chinese University of Hong Kong, Hong Kong, Hong Kong SAR, China.
Frontiers in artificial intelligence
|February 16, 2026
Resumen
Este estudio presenta un marco de LLM para la predicción de redes de mercados financieros, mejorando las predicciones de riesgo sistémico y proporcionando información económica para los inversores.
Área de la Ciencia:
- Análisis de redes financieras
- Predicción de riesgo sistémico
- Aprendizaje automático en finanzas
Sus antecedentes:
- Los mercados financieros son redes complejas donde las tenencias institucionales influyen en el flujo de información y la propagación del riesgo.
- La predicción de la evolución de la red de acciones es crucial para la estabilidad, pero es un desafío debido a la complejidad de los datos y la no estacionariedad.
Objetivo del estudio:
- Desarrollar un marco de predicción interpretable basado en LLM para redes financieras.
- Predecir la concentración en todo el mercado y las anomalías a nivel de empresa para la detección temprana de riesgos.
Principales métodos:
- Se construyeron grafos bipartitos de fondos-acciones indexados por tiempo desde 2016 hasta 2024.
- Se calcularon indicadores de red: centralización de grado (cen_d) y densidad residual (den).
- Se desarrolló un marco de LLM que integra series temporales, divulgaciones textuales y contexto de recuperación aumentada para la predicción multietapa.
Principales resultados:
- El marco de LLM superó significativamente a los puntos de referencia ARIMA, Prophet y Temporal Fusion Transformer en precisión.
- El análisis de atención reveló la importancia del modelo para los trimestres con coinversión de fondos o shocks de políticas.
- Se demostró una reducción de errores y una mejora de la precisión direccional en la predicción de indicadores de red.
Conclusiones:
- La predicción impulsada por LLM ofrece advertencias tempranas sobre el riesgo sistémico e información interpretable.
- La predicción de grafos informada por el lenguaje presenta un nuevo paradigma para la vigilancia del mercado financiero y la política.
Videos de Conceptos Relacionados
Time-Series Graph
5.3K
A time-series graph is a line graph with repeated measurements taken at successive intervals of time. It is also called a time series chart. To construct a time-series graph, one must look at both pieces of a paired data set. The horizontal axis is used to plot the time increments, and the vertical axis is used to plot the values of the variable that one is measuring. By using the axes in this way, each point on the graph will correspond to time and a measured quantity. The points on the graph...
5.3K
Econometric Views (EViews)
609
Econometric Views, often stylized as EViews, is a package that merges statistical analysis with econometric studies. It is designed to provide tools for time series analysis, forecasting, and econometric model simulation. The software originated from MicroTSP software and has evolved significantly since its inception in 1981. The history of EViews is marked by a continuous effort to enhance its computational speed and user interface. It was initially developed for large computing systems but...
609
Prediction Intervals
3.4K
The interval estimate of any variable is known as the prediction interval. It helps decide if a point estimate is dependable.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
3.4K
First Derivative Test: Problem Solving
76
Imagine an asset price that crashes to a low point, rebounds sharply as bargain-hunters step in, and then gradually declines. Such behavior can be modeled with a smooth function whose turning points represent locally overvalued and undervalued regions. A convenient example that captures rebound followed by decay is:The high and low points of this curve are identified using the first derivative test, which determines where the function changes from increasing to decreasing or vice versa. To...
76
Exponential Equations for Modeling Growth
268
Exponential models are essential for describing rapid, multiplicative changes in natural systems, such as population growth. When a population doubles at regular intervals, the process can be modeled using a suitable base. For instance, a bacterial culture that doubles every three hours follows the model n(t)=n0⋅2t/3, where n(t) is the population at the time t.A more general model uses the natural base e, especially for continuous growth. This takes the form n(t)=n0⋅ert, where r is...
268
Quantitative Analysis
1.5K
Quantitative analysis is a technique for measuring the amount of specific constituents in a sample. When the sample's composition is unknown, qualitative analysis is performed first to identify its components, which ensures that the correct substances are measured during the quantitative phase.
In quantitative analysis, two key measurements are made: the sample quantity and a property proportional to the amount of the analyte (the substance being analyzed). This forms the basis of the...
In quantitative analysis, two key measurements are made: the sample quantity and a property proportional to the amount of the analyte (the substance being analyzed). This forms the basis of the...
1.5K