Abstract: Abstract Data-driven technologies have been changing every aspect of human life and the fast-developing banking sector with its data-rich nature has become the implementation field of these fast-evolving technologies. Deep learning, as one of the emerging technologies in recent years, has also been inevitably adopted for various improvements in banking. To the best of our knowledge, there is no comprehensive literature review, which focuses on specifically deep learning and its implementations in banking. Therefore, this paper investigates the deep learning technology in-depth and summarizes the relevant applications in banking so to contribute to the existing literature. Moreover, by providing a reliable and up-to-date review, it is also aimed to serve as the one-stop repository for banks and researchers who are interested in embracing deep learning, whilst bringing insights for the directions of future research and implementation. PubDate: 2020-06-29
Abstract: Abstract The statistical analysis in presence of missing data in any study is challenging. It gets more attention since last few years for clinical trials. There are several reasons for the occurrence of missing data in the crossover trial. However, attempts toward crossover trial data are negligible. This manuscript is dedicated towards development of missing data handling technique for three arms three periods crossover trial.Data obtained from a crossover trial having microarray gene expression values are considered. The gene expression values are considered as outcomes with therapeutic effects. The statistical methodology are explained through Multiple Imputation and Bayesian approach separately. Further, their performance with same data is documented. In Bayesian context, it becomes feasible to perform the causal effect relation jointly with imputation. However, we failed to perform it through mixed effect model jointly. We performed separately Multiple Imputation procedures to overcome the missing values in the dataset and thereafter performed with the mixed effect model to explore the causal effect relation between therapeutic arm on gene expression values. PubDate: 2020-06-25
Abstract: Abstract Streaming data models refer to some constrained settings through which continuous flow of information regarding updates on the data becomes available. Graphs can also be represented in a streaming setting where interaction information turns out to be accessible as a stream of inclusion or exclusion of interactions. Analysis of streaming graphs helps to understand extreme-scale and dynamic real-life interactions in different forms. The growth of world wide web has drastically changed the way we look at various real-life evolving gigantic networks. This has motivated the development of streaming algorithms to be applied on graphs at scale. To achieve this scalability, sketching and sampling strategies are generally adopted to realize the different attributes of graphs. Spectrum of a graph, being one of the most appreciated characteristics, has lead to the evolution of an entire class of spectral algorithms. In this paper, we touch upon the state-of-the-art progress in streaming graph analysis with spectral algorithms. We mainly cover the latest developments in the areas like sampling, sparsification, singular value decomposition, counting problems related to local structures, analysis of global structures, partitioning, labeling, mesh processing, discovery of patterns, anomalous hotspot discovery, detection of communities, etc. on the subject of streaming graphs. PubDate: 2020-06-25
Abstract: Abstract Characterization and quantification of the tail behaviour of rare events is an important issue in financial risk management. In this paper, the extreme behaviour of stock market returns from BRICS over the period 1995–2015 is described using five parametric distributions based on extreme value theory, including two mixture distributions based on the student’s t distribution. The distributions are fitted to the data using the method of maximum likelihood. The generalized extreme value (GEV) distribution is found to give the best fit. Based on the GEV distribution, estimates of value at risk, \({\hbox {VaR}}_{p}(X)\) and expected shortfall, \({\hbox {ES}}_{p}(X)\) from the five countries are computed. In addition, the correlation structure and tail dependence of these markets are characterized using several copula models. The Gumbel copula gives the best fit with evidence of significant relationships for all the pairs of the markets. To account for the possibility that due to sampling variability, a different model might be selected as the preferred model in a new sample from the same population, a short bootstrapping exercise was performed. PubDate: 2020-06-22
Abstract: Abstract Let a progressively type-II (PT-II) censored sample of size m is available. Under this set-up, we consider the problem of estimating unknown model parameters and two reliability characteristics of the log-logistic distribution. Maximum likelihood estimates (MLEs) are obtained. We use expectation–maximization (EM) algorithm. The observed Fisher information matrix is computed. We propose Bayes estimates with respect to various loss functions. In this purpose, we adopt Lindley’s approximation and importance sampling methods. Asymptotic and bootstrap confidence intervals are derived. Asymptotic intervals are obtained using two approaches: normal approximation to MLEs and log-transformed MLEs. The bootstrap intervals are computed using boot-t and boot-p algorithms. Further, highest posterior density (HPD) credible intervals are constructed. Two sets of practical data are analyzed for the illustration purpose. Finally, detailed simulation study is carried out to observe the performance of the proposed methods. PubDate: 2020-06-14
Abstract: Abstract The inverse Weibull distribution is successfully applied in many different disciplines e.g., reliability engineering, bioengineering and modeling of survival data. There are lots of statistical and computer science techniques e.g., particle swarm optimization, employed to estimate the parameters of this distribution and its generalization. The suitable methods for estimating the parameters of Marshall–Olkin extended inverse Weibull distribution are specified in this paper. So, the performance of different estimation methods called maximum likelihood, Percentiles, Least squares, Weighted least squares, Cramér–van Mises and Anderson–Darling methods, is compared in terms of the bias and mean squared error through extensive numerical simulations. Also, empirical illustration on real life dataset supported the obtained conclusion. PubDate: 2020-06-13
Abstract: Abstract Inverse xgamma distribution is recently proposed by Yadav et al. (J Ind Prod Eng 35(1):48–55, 2018) as an inverted version of xgamma distribution. In the present article, some more statistical properties (such as, characteristic and generating functions, distributions of extreme order statistics, important entropy measures) and some additional survival and/or reliability characteristics (such as, conditional moments, mean deviation, Bonferroni and Lorenz curves, entropy, ageing intensity) of inverse xgamma distribution have been studied in detail. Classical and Bayesian inferential procedures to estimate the unknown parameter, reliability function, hazard rate function under progressively censored schemes have been investigated. Further, asymptotic confidence interval (ACI), bootstrap confidence interval (BCI) and highest posterior density (HPD) credible interval for the parameter have also been calculated. A Monte-Carlo simulation study has been performed to compare the performances of classical and Bayesian estimators of reliability function and hazard rate function. The performances of ACI, BCI and HPD credible intervals have been compared in terms of estimated average widths and coverage probabilities for the parameter. Lastly, a data set is analyzed for illustrating the proposed methodology. PubDate: 2020-06-13
Abstract: Abstract This paper is concerned with the estimation problem using maximum likelihood method of estimation for the unknown parameters of exponetiated gumbel distribution based on neoteric ranked set sampling (NRSS) as a new modification of the usual ranked set sampling (RSS) technique. Numerical study is conducted to compare NRSS as a dependent ranked set sampling technique, with RSS, and median ranked set sampling as independent sampling techniques, and then the performance of RSS and its modifications will be compared with simple random sampling based on their mean square errors and efficiencies. PubDate: 2020-06-12
Abstract: Abstract The choice of variable-selection methods to identify important variables for binary classification modeling is critical for producing stable statistical models that are interpretable, that generate accurate predictions, and have minimal bias. This work is motivated by the availability of data on clinical and laboratory features of dengue fever infections obtained from 51 individuals enrolled in a prospective observational study of acute human dengue infections. Our paper uses objective Bayesian method to identify important variables for dengue hemorrhagic fever (DHF) over the dengue data set. With the selected important variables by objective Bayesian method, we employ a Gaussian copula marginal regression model considering correlation error structure and a general method of semi-parametric Bayesian inference for Gaussian copula model to estimate, separately, the marginal distribution and dependence structure. We also carry out a receiver operating characteristic (ROC) analysis for the predictive model for DHF and compare our proposed model with the other models of Ju and Brasier (Variable selection methods for developing a biomarker panel for prediction of dengue hemorrhagic fever. BMC Res Notes 6:365, 2013) tested on the basis of the ROC analysis. Our results extend the previous models of DHF by suggesting that IL-10, Days Fever, Sex and Lymphocytes are the major features for predicting DHF on the basis of blood chemistries and cytokine measurements. In addition, the dependence structure of these Days Fever, Lymphocytes, IL-10 and Sex protein profiles associated with disease outcomes was discovered by the semi-parametric Bayesian Gaussian copula model and Gaussian partial correlation method. PubDate: 2020-06-10
Abstract: Abstract In this paper, a new three-parameter unit probability distribution is proposed. The new model is a generalization of Burr III distribution, and it is more flexible than some existing well-known distribution due to its different shapes of the hazard function and probability density functions. The mathematical properties of this distribution are presented, including moments, reliability measures, mean residual life, and characterizations, and we also propose a modified Chi squared goodness-of-fit test based on Nikulin–Rao–Robson statistic Y2 in the presence of complete and censored data. The parameters related to the proposed distribution are estimated using well-known estimation methods. A numerical simulations study is conducted for reinforcement of the results. In the end, we considered two real datasets to illustrate the applicability of the proposed model. PubDate: 2020-06-08
Abstract: Abstract We introduced and studied a new three-parameter lifetime distribution based on Marshall–Olkin and inverted Nadarajah–Haghighi distribution. In comparison with some existing lifetime models, the new distribution has very flexible shapes for hazard rate as well as for the probability density function. The related mathematical functions of the new distribution are presented. The maximum likelihood method is considered to obtain the parameter estimates of the MOINH distribution. A simulation study is presented to assess the behavior of the proposed estimator. The potentiality of the distribution is illustrated by fitting two real data sets. PubDate: 2020-06-08
Abstract: Abstract This paper proposes a novel unsupervised document embedding based clustering algorithm to generate clinical note templates. We adapted Charikar’s SimHash to embed each clinical document into a vector representation. We modified the traditional K-means algorithm to merge any two clusters with centroids when they are very close. Under the K-means paradigm, our algorithm designates the cluster representative corresponding to the document vector closest to the centroid as the prototype template. On a corpus of clinical notes, we evaluated the feasibility of utilizing our algorithm at the individual author level. The corpus contains 1,063,893 clinical notes corresponding to 19,146 unique providers between January 2011 and July 2016. Our algorithm achieved more than 80% precision and runs in O(n) time complexity. We further validated our algorithm using human annotators who reported it is able to efficiently detect a real clinical document that can represent the other documents in the same cluster at both the department level and the individual clinician level. PubDate: 2020-06-06
Abstract: Abstract In this paper, we establish the explicit expressions and some recurrence relations for single and product moments of order statistics from exponentiated Burr XII distribution. By using, these results we can calculate the mean and variances based on order statistics for the given distribution. PubDate: 2020-06-03
Abstract: Abstract The analysis of time-varying correlation between stock prices and exchange rates in the context of international investments has been well researched in the literature in last few years. In this paper, we study the interdependence of exchange rates and stock prices for seven countries (Canada, Japan, Denmark, Hong Kong, Singapore, Mexico and Brazil). To do so, we both use the DCC-FIEGARCH and FIAPARCH-DCC models during the period spanning from January 1, 2000 until January 1, 2016. The empirical results suggest asymmetric responses in stock prices-exchange rates linkages, a high persistence of the conditional correlation. They also show bidirectional spillovers effects between different series. Moreover, the results indicate different behavior of exchange rates-stock prices nexus during the crisis periods, suggesting the need for specific policy measures. Finally, our findings offer investors, portfolios managers and policymakers insights on international portfolios and monetary. PubDate: 2020-06-03
Abstract: Abstract In this article, a new method is suggested to expand a family of life distributions by adding an additional parameter. The new proposal may be named as the Zubair-G family of distributions. For this family, general expressions for some mathematical properties are derived. The maximum product spacing, ordinary least square and maximum likelihood methods are discussed to estimate the model parameters. A three-parameter special sub-model of the proposed family, called the Zubair–Weibull distribution is considered in detail. Its density function can be symmetrical, left-skewed, right-skewed, and has increasing, decreasing, bathtub and upside-down bathtub shaped failure rates. To illustrate the importance of the proposed family over the other well-known methods, two applications to real data sets are analyzed. PubDate: 2020-06-01
Abstract: Abstract In this paper, we derive the likelihood function of the neoteric ranked set sampling (NRSS) as dependent in sampling method and double neoteric ranked set sampling (DNRSS) designs as combine between independent sampling method in the first stage and dependent sampling method in the second stage and they compared for the estimation of the parameters of the inverse Weibull (IW) distribution. An intensive simulation has been made to compare the one and the two stages designs. The results showed that likelihood estimation based on ranked set sampling (RSS) as independent sampling method, NRSS and DNRSS designs provide more efficient estimators than the usual simple random sampling design. Moreover, the DNRSS is slightly more efficient than the NRSS and RSS designs in the case of estimating the IW distribution parameters. PubDate: 2020-06-01
Abstract: Abstract This paper describes the classical and Bayesian inferences for the generalized DUS exponential distribution under type-I progressive hybrid censored data. In classical estimation; maximum likelihood estimator is used for obtaining estimates of the parameters. While in Bayesian context; two different losses namely squared error and linex loss function are used for estimation purpose. Metropolis–Hasting algorithm has applied to generate Markov chain Monte Carlo samples from the posterior density. In case of interval estimation; asymptotic confidence intervals and highest posterior density intervals for the unknown parameters are computed. The performance of estimators for different value of the parameters have done on the basis of mean square errors and risks. Lastly, a dataset is used to illustrate the proposed censoring methodology in a real-world situation. PubDate: 2020-05-02
Abstract: Abstract Points of distribution, sales or service are important elements of the supply chain. These are the final elements which are responsible for proper functioning of the whole cargo distribution process. Proper location of these points in the transport network is essential to ensure the effectiveness and reliability of the supply chain. The location of these points is very important also from the consumer’s point of view. In this paper, a mathematical model is proposed to design of a post supply chain network to minimize transportation cost, facilities location cost and holding cost. The proposed supply chain network consists of four echelons: supplier, post office, distribution center, and recipient. The bold point of this study is as regards the post supply chain is examined, the demand of the recipient’s point determines in supplier point not in delivery point. Finally, the proposed model is solved by LINGO 17 software and the results are analyzed. PubDate: 2020-04-29
Abstract: Abstract This paper is a study on three multivariate data sets using some factor analysis techniques in the literature. The techniques are: the principal factor method (PFM), maximum likelihood factor analysis (MLFA), the classical principal component method (PCM) and the refined principal component method (rPCM). The computations are carried out using the statistical package for the social sciences (SPSS), Minitab and MATLAB. Findings reveal that the rPCM generates results as that of the PCM and that the rPCM and the PCM are more appropriate for exploratory factor analysis than the PFM and MLFA as the PFM and the MLFA may fail to converge or may yield a Heywood case. PubDate: 2020-04-24
Abstract: Abstract Android has become a leader in market share of mobile operating systems. In addition, it has attracted interest of attackers greater than other running systems. As a result, Android malware is developing rapidly. In this study, the foremost focal point is on inspecting and detecting botnets that are particular type of malwares. To analyze android botnet detection, it is appropriate to pick out and analyze elements which are enormously applicable or most influential to the botnet detection. This technique typically named variable determination is corresponds to determine a subset of complete recorded variables which presents favorable predictions capability. In this research work, architecture based totally upon adaptive neuro-fuzzy inference system (ANFIS) is used to model complex systems in function approximation and regression. ANFIS community is employed to operate variable selection for identifying that how the botnet have an effect on the android. After deciding on the two most influential parameters, the ANFIS is utilized to create a machine for android botnet detection on the foundation of the chosen parameters. PubDate: 2020-04-17
Hybrid journal (It can contain Open Access articles)
[2626 journals]
