Abstract The prediction of financial markets is a challenging yet important task. In modern electronically driven markets, traditional time‐series econometric methods often appear incapable capturing the true complexity multilevel interactions driving price dynamics. While recent research has established effectiveness machine learning (ML) models in applications, their intrinsic inability to deal with uncertainties, which great concern econometrics and real business constitutes major...

Deep Learning models have become dominant in tackling financial time-series analysis problems, overturning conventional machine learning and statistical methods. Most often, a model trained for one market or security cannot be directly applied to another due differences inherent the conditions. In addition, as evolves over time, it is necessary update existing train new ones when data made available. This scenario, which most forecasting applications, naturally raises following research...

Financial time-series forecasting is one of the most challenging domains in field analysis. This mostly due to highly non-stationary and noisy nature financial data. With progressive efforts community design specialized neural networks incorporating prior domain knowledge, many analysis problems have been successfully tackled. The temporal attention mechanism a layer that recently gained popular-ity its ability focus on important events. In this paper, we propose based ideas multi-head...

Purpose The purpose of this paper is to propose a new methodology that handles the issue dynamic behavior customers over time. Design/methodology/approach A presented based on time series clustering extract dominant behavioral patterns This implemented using bank customers’ transactions data which are in form data. include recency (R), frequency (F) and monetary (M) attributes businesses point-of-sale (POS) bank. were obtained from analysis department Findings After carrying out an empirical...

Abstract Cross-correlation analysis is a powerful tool for understanding the mutual dynamics of time series. This study introduces new method predicting future state synchronization two financial To this end, we use cross recurrence plot as nonlinear quantifying multidimensional coupling in domain series and determining their synchronization. We adopt deep learning framework methodologically addressing prediction based on features extracted from dynamically sub-sampled plots. provide...

Online reviews are crucial resources both for users and business enterprises. However, the quality of online varies greatly. To address problem low-quality reviews, we focus on reviewer credibility propose a new framework. The proposed framework incorporates three main parts including identification source factors, preprocessing, ranking via interval type-2 fuzzy analytical hierarchy process (IT2FAHP) VIKOR method. A major distinction is utilising multiple factors obtained from different...

We propose an optimization algorithm for variational inference (VI) in complex models. Our approach relies on natural gradient updates where the space is a Riemann manifold. develop efficient gaussian whose satisfy positive definite constraint covariance matrix. manifold Bayes precision matrix (MGVBP) solution provides simple update rules, straightforward to implement, and use of parameterization has significant computational advantage. Due its black-box nature, MGVBP stands as ready-to-use...

Financial market analysis, especially the prediction of movements stock prices, is a challenging problem. The nature financial time-series data, being non-stationary and nonlinear, main cause these challenges. Deep learning models have led to significant performance improvements in many problems coming from different domains, including data. Although goal such models, dealing with ultra high-frequency data sets restrictions terms number model parameters its inference speed. Temporal...

Deep Learning models have become dominant in tackling financial time-series analysis problems, overturning conventional machine learning and statistical methods. Most often, a model trained for one market or security cannot be directly applied to another due differences inherent the conditions. In addition, as evolves over time, it is necessary update existing train new ones when data made available. This scenario, which most forecasting applications, naturally raises following research...

We develop an optimization algorithm suitable for Bayesian learning in complex models. Our approach relies on natural gradient updates within a general black-box framework efficient training with limited model-specific derivations. It applies the class of exponential-family variational posterior distributions, which we extensively discuss Gaussian case have rather simple form. Quasi Black-box Variational Inference (QBVI) is readily applicable to wide inference problems and implementation as...

Online reviews are crucial resources both for users and business enterprises. However, the quality of online varies greatly. To address problem low-quality reviews, we focus on reviewer credibility propose a new framework. The proposed framework incorporates three main parts including identification source factors, preprocessing, ranking via interval type-2 fuzzy analytical hierarchy process (IT2FAHP) VIKOR method. A major distinction is utilising multiple factors obtained from different...

User-Generated-Content (UGC) in the form of online reviews can be an invaluable source information for both customers and businesses. Sentiment analysis opinion mining tools techniques have been proposed literature to extract knowledge from reviews. Aspect-based which has gained growing attention mainly two tasks including aspect extraction sentiment polarity detection. Once aspect-based task accomplished; a bag sentiments will achieved. In many cases, it is necessary obtain overall about...

Financial time-series forecasting is one of the most challenging domains in field analysis. This mostly due to highly non-stationary and noisy nature financial data. With progressive efforts community design specialized neural networks incorporating prior domain knowledge, many analysis problems have been successfully tackled. The temporal attention mechanism a layer that recently gained popularity its ability focus on important events. In this paper, we propose based ideas multi-head extend...

Deep Learning models have become dominant in tackling financial time-series analysis problems, overturning conventional machine learning and statistical methods. Most often, a model trained for one market or security cannot be directly applied to another due differences inherent the conditions. In addition, as evolves through time, it is necessary update existing train new ones when data made available. This scenario, which most forecasting applications, naturally raises following research...

Cross-correlation analysis is a powerful tool for understanding the mutual dynamics of time series. This study introduces new method predicting future state synchronization two financial To this end, we use cross-recurrence plot as nonlinear quantifying multidimensional coupling in domain series and determining their synchronization. We adopt deep learning framework methodologically addressing prediction based on features extracted from dynamically sub-sampled plots. provide extensive...

We propose an optimization algorithm for Variational Inference (VI) in complex models. Our approach relies on natural gradient updates where the variational space is a Riemann manifold. develop efficient Gaussian whose satisfy positive definite constraint covariance matrix. Manifold Bayes Precision matrix (MGVBP) solution provides simple update rules, straightforward to implement, and use of precision parametrization has significant computational advantage. Due its black-box nature, MGVBP...

Cross-correlation analysis is a powerful tool for understanding the mutual dynamics of time series.This study introduces new method predicting future state synchronization two financial series. To this end, we use cross-recurrence plot as nonlinear quantifying multidimensional coupling in domain series and determining their synchronization. We adopt deep learning framework methodologically addressing prediction based on features extracted from dynamically sub-sampled plots. provide extensive...

The prediction of financial markets is a challenging yet important task. In modern electronically-driven markets, traditional time-series econometric methods often appear incapable capturing the true complexity multi-level interactions driving price dynamics. While recent research has established effectiveness machine learning (ML) models in applications, their intrinsic inability to deal with uncertainties, which great concern econometrics and real business constitutes major drawback....