Search results

This study explores whether a new machine learning method can more accurately predict the movement of stock prices.

This study presents a novel hybrid deep learning model, Residual-CNN-Seq2Seq (RCSNet), to predict the trend of stock price movement. RCSNet integrates the autoregressive integrated moving average (ARIMA) model, convolutional neural network (CNN) and the sequence-to-sequence (Seq2Seq) long–short-term memory (LSTM) model.

The hybrid model is able to forecast both linear and non-linear time-series component of stock dataset. CNN and Seq2Seq LSTMs can be effectively combined for dynamic modeling of short- and long-term-dependent patterns in non-linear time series forecast. Experimental results show that the proposed model outperforms baseline models on S&P 500 index stock dataset from January 2000 to August 2016.

This study develops the RCSNet hybrid model to tackle the challenge by combining both linear and non-linear models. New evidence has been obtained in predicting the movement of stock market prices.

This study examines the impact of hedging on firm value of Sharīʿah compliant firms (SCFs) in a non-linear framework.

This study employs the system-GMM for dynamic panel data to examine the influence of derivatives usage on firm value (Tobin's Q, ROA and ROE). The sample comprised of 59 non-financial SCFs engaged in derivatives from 2000 to 2017 (18 years). The Sasabuchi-Lind-Mehlum (SLM) test for U-shaped is performed to confirm the existence of the non-linear relationship.

This study concludes that hedging significantly contributes to firm value of SCFs based on the non-linear framework. This study suggests that, first, the non-linear relationship occurs due to the different degree of derivatives usage and risk. Second, firms practice selective hedging to maintain the upside potential of firm value.

This study has important implications. First, the importance of risk management via derivatives to increase firm value, second, the evidence of selective hedging from the non-linear relationship between derivatives and firm value and third, the need for quality reporting on derivatives engagement by firms in line with the required accounting standard on derivatives.

This study fills the gap in the literature in relation to the risk management strategies of SCFs in three aspects. First, re-examines the relationship using recent data. Second, examines the relationship in the non-linear framework as the limited studies found in the literature on Malaysian firms are only based on linear relationship. Third, determines whether hedging undertaken by firms is optimal as this can only be addressed using the non-linear framework. This study is robust to the various definitions of firm value (Tobin's Q, ROA and ROE) and non-linear methodologies.

This study aims to analyse the non-linear losses of a porous media (stack) composed by parallel plates and inserted in a resonator tube in oscillatory flows by proposing numerical correlations between pressure gradient and velocity.

The numerical correlations origin from computational fluid dynamics simulations, conducted at the microscopic scale, in which three fluid channels representing the porous media are taken into account. More specifically, for a specific frequency and stack porosity, the oscillating pressure input is varied, and the velocity and the pressure-drop are post-processed in the frequency domain (Fast Fourier Transform analysis).

It emerges that the viscous component of pressure drop follows a quadratic trend with respect to velocity inside the stack, while the inertial component is linear also at high-velocity regimes. Furthermore, the non-linear coefficient b of the correlation ax + bx² (related to the Forchheimer coefficient) is discovered to be dependent on frequency. The largest value of the b is found at low frequencies as the fluid particle displacement is comparable to the stack length. Furthermore, the lower the porosity the higher the Forchheimer term because the velocity gradients at the stack geometrical discontinuities are more pronounced.

The main novelty of this work is that, for the first time, non-linear losses of a parallel plate stack are investigated from a macroscopic point of view and summarised into a non-linear correlation, similar to the steady-state and well-known Darcy–Forchheimer law. The main difference is that it considers the frequency dependence of both Darcy and Forchheimer terms. The results can be used to enhance the analysis and design of thermoacoustic devices, which use the kind of stacks studied in the present work.

This study aims to propose a non-linear model to describe the effect of macroeconomic shocks on delinquency rates of three kinds of bank loans. Indeed, a wealth of literature has recognized significant evidence of the linkage between macro conditions and credit vulnerability, perceiving the importance of the high amount of bad loans for economic stagnation and financial vulnerability.

Generally, this linkage was represented by linear relationships, but the strong dependence of bank loan default on the economic cycle, subject to changes in regime, could suggest non-linear models as more appropriate. Indeed, macroeconomic variables affect the performance of bank’s portfolio loan, but such a relationship is subject to changes disturbing the stability of parameters along the time. This study is an attempt to model three different kinds of bank loan defaults and to forecast them in the case of the USA, detecting non-linear and asymmetric behaviors by the adoption of a Markov-switching (MS) approach.

Comparing it with the classical linear model, the authors identify evidence for the presence of regimes and asymmetries, changing in correspondence of the recession periods during the span of 1987–2017.

The data are at a quarterly frequency, and more observations and more extended research periods could ameliorate the MS technique.

The good forecasting performance of this model could be applied by authorities to fine-tune their policies and deal with different types of loans and to diversify strategies during the different economic trends. In addition, bank management can refer to the performance of macroeconomic conditions to predict the performance of their bad loans.

The authors show a clear outperformance of the MS model concerning the linear one.

The purpose of this study is to account for a recent non-mainstream econometric approach using microdata and how it can inform research in business administration. More specifically, the paper draws from the applied microeconometric literature stances in favor of fitting Poisson regression with robust standard errors rather than the OLS linear regression of a log-transformed dependent variable. In addition, the authors point to the appropriate Stata coding and take into account the possibility of failing to check for the existence of the estimates – convergency issues – as well as being sensitive to numerical problems.

The author details the main issues with the log-linear model, drawing from the applied econometric literature in favor of estimating multiplicative models for non-count data. Then, he provides the Stata commands and illustrates the differences in the coefficient and standard errors between both OLS and Poisson models using the health expenditure dataset from the RAND Health Insurance Experiment (RHIE).

The results indicate that the use of Poisson pseudo maximum likelihood estimators yield better results that the log-linear model, as well as other alternative models, such as Tobit and two-part models.

The originality of this study lies in demonstrating an alternative microeconometric technique to deal with positive skewness of dependent variables.

The purpose of this paper is to unpack the underlying mechanisms of entrepreneurs' passion, orientation and behavior by investigating the role of rational and nonrational cognitive elements. Building on dual process theory and sociointuitionism, a conceptual model is proposed in order to explore the relationship between entrepreneurial passion, entrepreneurial orientation (EO) and strategic entrepreneurship behavior (SEB). Specifically, entrepreneurs' linear thinking styles (System 2) and nonlinear thinking styles (System 1) are hypothesized as being significant moderators of such a relationship.

Covariance-based structural equation modeling (CB-SEM) is used to empirically validate the proposed conceptual model and test the moderating hypotheses on a sample of 300 entrepreneurs actively involved in European small and medium enterprises (SMEs).

Entrepreneurial passion is shown to be a significant antecedent of EO, which, in turn, strongly influences SEB. Moreover, entrepreneurs' linear thinking style positively moderates the EO-SEB relationship, but not the link between passion and EO. Instead, a nonlinear thinking style positively moderates the relationship between passion and EO, but not the links between EO and SEB.

Entrepreneurs should trust their nonlinear thinking style – related to affective/emotive and intuitive information processing systems – to foster the effect of their entrepreneurial passion on EO. Furthermore, entrepreneurs should rely on a linear thinking style, namely the rational and deliberative cognitive processes, to enhance the impact of their EO on SEB.

Dual process theory and sociointuitionism are integrated to simultaneously investigate the effect of nonrational and rational cognitive mechanisms on entrepreneurs' orientation and behavior. Moreover, the proposed model is empirically tested on a sample of entrepreneurs working in SMEs located in Europe, which have received little attention from entrepreneurship scholars in comparison to their US counterparts. The authors’ findings suggest important implications for entrepreneurs, policymakers and entrepreneurial universities educators.

Inspired by the basic idea of gradient boosting, this study aims to design a novel multivariate regression ensemble algorithm RegBoost by using multivariate linear regression as a weak predictor.

To achieve nonlinearity after combining all linear regression predictors, the training data is divided into two branches according to the prediction results using the current weak predictor. The linear regression modeling is recursively executed in two branches. In the test phase, test data is distributed to a specific branch to continue with the next weak predictor. The final result is the sum of all weak predictors across the entire path.

Through comparison experiments, it is found that the algorithm RegBoost can achieve similar performance to the gradient boosted decision tree (GBDT). The algorithm is very effective compared to linear regression.

This paper attempts to design a novel regression algorithm RegBoost with reference to GBDT. To the best of the knowledge, for the first time, RegBoost uses linear regression as a weak predictor, and combine with gradient boosting to build an ensemble algorithm.

The purpose of this paper is to analyze numerically the blowup in finite time of the solutions to a one-dimensional, bidirectional, nonlinear wave model equation for the propagation of small-amplitude waves in shallow water, as a function of the relaxation time, linear and nonlinear drift, power of the nonlinear advection flux, viscosity coefficient, viscous attenuation, and amplitude, smoothness and width of three types of initial conditions.

An implicit, first-order accurate in time, finite difference method valid for semipositive relaxation times has been used to solve the equation in a truncated domain for three different initial conditions, a first-order time derivative initially equal to zero and several constant wave speeds.

The numerical experiments show a very rapid transient from the initial conditions to the formation of a leading propagating wave, whose duration depends strongly on the shape, amplitude and width of the initial data as well as on the coefficients of the bidirectional equation. The blowup times for the triangular conditions have been found to be larger than those for the Gaussian ones, and the latter are larger than those for rectangular conditions, thus indicating that the blowup time decreases as the smoothness of the initial conditions decreases. The blowup time has also been found to decrease as the relaxation time, degree of nonlinearity, linear drift coefficient and amplitude of the initial conditions are increased, and as the width of the initial condition is decreased, but it increases as the viscosity coefficient is increased. No blowup has been observed for relaxation times smaller than one-hundredth, viscosity coefficients larger than ten-thousandths, quadratic and cubic nonlinearities, and initial Gaussian, triangular and rectangular conditions of unity amplitude.

The blowup of a one-dimensional, bidirectional equation that is a model for the propagation of waves in shallow water, longitudinal displacement in homogeneous viscoelastic bars, nerve conduction, nonlinear acoustics and heat transfer in very small devices and/or at very high transfer rates has been determined numerically as a function of the linear and nonlinear drift coefficients, power of the nonlinear drift, viscosity coefficient, viscous attenuation, and amplitude, smoothness and width of the initial conditions for nonzero relaxation times.

This paper aims to investigate the possible non-linear effect of net working capital (NWC) level on profitability for Middle East and North Africa (MENA) region listed companies. Furthermore, the study tests the possible interactive effect of cash levels on the relationship between NWC and profitability.

NWC level is the independent variable and profitability is the dependent variable using two proxies, return on assets (ROA) and returns on equity (ROE). Control variables are size, leverage, gross domestic product growth and sales revenue growth. The generalized method of moments was used to analyze the data of 134 consumer-goods listed firms in 12 MENA countries for the period 2013–2019.

The results demonstrate that NWC levels had a non-linear effect on profitability using ROA as a profitability proxy while results were insignificant using ROE as a profitability proxy. Furthermore, results show the absence of interactive effects between NWC, cash levels and both profitability proxies.

The study fills a gap in the working capital management (WCM) literature by providing new evidence on WCM’s non-linear effect of corporate performance in the MENA region emerging markets using the consumer-goods industry sample. The study contributes to the financial managers’ working capital optimization efforts in the MENA region by providing evidence on the usefulness of WC optimization efforts in the region from a financial performance point of view. According to the researchers’ knowledge, a few studies attempted to investigate this non-linear relationship for neither MENA region countries nor the consumer-goods industry.

Diabetes is a major metabolic disorder which can affect entire body system adversely. Undiagnosed diabetes can increase the risk of cardiac stroke, diabetic nephropathy and other disorders. All over the world millions of people are affected by this disease. Early detection of diabetes is very important to maintain a healthy life. This disease is a reason of global concern as the cases of diabetes are rising rapidly. Machine learning (ML) is a computational method for automatic learning from experience and improves the performance to make more accurate predictions. In the current research we have utilized machine learning technique in Pima Indian diabetes dataset to develop trends and detect patterns with risk factors using R data manipulation tool. To classify the patients into diabetic and non-diabetic we have developed and analyzed five different predictive models using R data manipulation tool. For this purpose we used supervised machine learning algorithms namely linear kernel support vector machine (SVM-linear), radial basis function (RBF) kernel support vector machine, k-nearest neighbour (k-NN), artificial neural network (ANN) and multifactor dimensionality reduction (MDR).