Showing papers in "The Journal of Finance and Data Science in 2016"

TL;DR: The novelty of the approach is to engender the profitable stock trading decision points through integration of the learning ability of CEFLANN neural network with the technical analysis rules.

TL;DR: This paper investigates both traditional feature learning algorithms and state-of-the-art deep learning models, and gives a few remarks on the development of data representation learning and suggest some interesting research directions in this area.

TL;DR: It is illustrated that the spectral optimization in SRA can be viewed as a relaxation of an unsupervised SVM problem, and it is demonstrated that the first non-principal eigenvector of a Laplacian matrix is linked to a bi-class classification strength measure which can be used to rank anomalies.

TL;DR: By comparing their classification performance, it is found that neural network outperforms many other machine learning techniques in classifying news category and that there are many challenges left for future development of textual analysis, such as identifying multiple objects within one single document.

TL;DR: In this paper, the authors used multivariate regression method to determine characteristics of stocks and firms that are deliberately affected by stock market crash occurring in Indonesia, and found that stocks with higher betas, larger capitalization, more return volatility, higher debt ratios, lower levels of liquid assets, and lower asset profitability tend to lose more value on crash day.

TL;DR: In this paper, the daily returns of four African countries' stock market indices for the period January 2, 2000, to December 31, 2014, were employed to compare the GARCH(1,1) model and a newly proposed Maximal Overlap Discreet Wavelet Transform (MODWT)-GARCH (1, 1) model.

TL;DR: In this article, the authors examined the nature of competition in banking sector of Pakistan and assessed whether the banking sector is in long-run equilibrium or not, using annual panel data for a sample of 30 banks, over the period 2007-2015 by employing Rosse and Panzar (1977) methodology.

TL;DR: In this article, the authors used the daily returns of four African countries' stock market indices for the period January 2, 2000, to December 31, 2014, and compared the linear Maximal Overlap Discreet Wavelet Transform MODWT-GARCH (1,1) model with the Maximal overlap discreet wavelet Transform-EGARCH model.

TL;DR: In this article, an extensive comparison of out-of-sample volatility and value-at-risk (VaR) forecast performance on three equity market indices: S&P500, FTSE100, and DAX30 using 13 risk models that consist of 5 GARCH specifications, 4 ARFIMAX specifications and 4 HARX specifications.

TL;DR: In this article, a pricing formula for arithmetic Asian options is derived by using the Edgeworth series expansion, which consists of a Black-Scholes-Merton type formula and a finite sum with the estimation of the remainder term.

TL;DR: An improved Firefly-Harmony search (IFFHS) learning algorithm is used to estimate the parameters of the consequent part and feedback loop parameters for better stability and convergence of the proposed LRNFIS model.

TL;DR: It is in general demonstrated that in all cases the proposed forecasting scheme outperforms other competitive methods.

TL;DR: In this article, the authors evaluate the daily conditional volatility and h-step-ahead value at risk forecasting power of three long memory GARCH-type models (FIGARCH, HYGARCH, and FIAPARCH).

TL;DR: In this article, the authors study the market microstructure around 4pm and demonstrate that market dynamics can be distinguished from other times during the day through increased volatility and size of movements, and question the aggregate benefit to the client base of using the WM/R 4pm fix in its current form.

TL;DR: In this paper, the authors extend the findings reported by Singh and Kaur 46 by considering pairwise volatility spillover effects among the US-BRIC equity markets and capturing the impact of overall US financial market conditions on pairwise variance of price discovery and volatility spillovers across the years 2004-2014 by employing diverse econometric models.

TL;DR: In this paper, the authors investigated the dynamic price transmissions of the dually listed BRICS shares traded in the US market based on a value-weighted portfolio using efficient estimation of vector error correction model containing exogenous I(1) variables or VECX*, and provided convincing evidence that in the short run the domestic and global destabilising factors cause varying levels of vulnerability in the BRICS stock and ADR portfolio price movements.

TL;DR: In this article, the authors analyzed the return-volatility relation for the New Third Board market in China and found evidence of a negative relation between the returns and the future changes of volatility.