درخت حوزه‌های تخصصی

Financial assessment has been of great interest to both academic and practitioners in the past decades. Among several performance assessment approaches, Data Envelopment Analysis (DEA) has become one of the crucial tools that have been commonly adopted to financially evaluate firms in various fields. The main aim of this review article is to review of DEA models in regarding to evaluation of the financial performance. This paper presents the first comprehensive and structured literature review of the use of DEA models for financially assessment. To this end, this paper reviewed and summarized the different models of DEA models that have been applied around the world to development of financial assessment problems. Consequently, a review of 455 published scholarly papers appearing in 160 journals between 1994 and 2021 have been obtained to achieve a comprehensive review of DEA application in financial efficiency. Accordingly, the selected articles have been categorized based on year of publication, authors, nationalities, scope of study, time duration, application area, study purpose, results, outcomes, etc. The discussion and the findings of this paper can be used as a guideline to analysts to determine the best fit financial assessment method when DEA evaluation is applied to any dataset. Future perspectives and challenges are discussed.

Predicting macroeconomic indicators is very important for policymakers and economists. Unemployment is one of the key indicators of macroeconomics that has adverse economic and social consequences. So far, many models have been proposed to predict this variable, but models in which accounting information was used to predict unemployment rate were ignored. The purpose of this paper is to investigate the relationship between aggregate cost stickiness, as one of the known variables in accounting, and unemployment rate. To this end, seasonal macro level time series data of Tehran Stock Exchange (TSE) and macroeconomic data are analyzed in two stages from 2008:2 to 2018:1. In the first stage, the relationship between these two variables is determined by specifying a linear regression model that is estimated using the OLS method. To investigate the predictive power of this model, the RMSE criterion was estimated in two scenarios with and without aggregate cost stickiness. Secondly, the reaction of the unemployment rate in response to a shock from aggregate cost stickiness is estimated by a Vector Autoregressive (VAR) model and the share of this variable is measured in the fluctuations of unemployment rate. The results show that aggregate cost stickiness improves the forecast of unemployment rate in the horizon previous. Also, the shock of aggregate cost stickiness explains about 6.5 percent of unemployment rate fluctuations.

Market manipulation remains the biggest concern of investors in today’s securities market. The development of technologies and complex trading algorithms seems to facilitate stock market manipulation and make it inevitable for regulators to use Deep Learning models to prevent manipulation. In this research, a Denoising GAN-based model has been designed. The proposed model (GAN-DAE4) consists of a three-layer encoder along with a 2-dimension encoder as the discriminator and a three-layer decoder as the generator. First, using statistical methods such as sequence, skewness, and kurtosis tests and some unsupervised learning methods such as Contextual Anomaly Detection (CAD) and some visual and graphical methods, the manipulated stocks have been detected in the Tehran Stock Exchange from 2015 to 2020; then GAN-DAE4 and some supervised deep learning models have been applied to the prepared data set. The results show that GAN-DAE4 outperformed other deep learning models (with F2-measure 73.71%) such as Decision Tree (C4.5), Random Forest, Neural Network, and Logistic Regression.

This research investigates the capital market's efficiency relative to the decreasing and increasing information the components of cash and accrual of the accounting earnings. In the accrual accounting system, accounting earnings includes two components of cash and accrual. Information about decreasing and increasing values of the normal and abnormal portion of the changes in financial assets as a cash component is compared with the information on the decreasing and increasing amounts of discretionary and non-discretionary accruals. The required data was extracted from the financial statements of the listed companies in Tehran Stock Exchange during the years 2003 to 2017. In order to estimate the research models from the regression with the combined data as well as the equations system, the simultaneous equations system with the seemingly unrelated regression (SUR) approach are utilized and then some experiments are implemented to evaluate the research hypotheses by using Mishkin’s test. The results reveal that the capital market is inefficient in terms of the increasing information (positive portion) of accrual and discretionary accruals and information on abnormal changes in financial assets (increasing and decreasing), but rather on the information (negative) of discretionary and non-discretionary accruals and abnormal changes in the financial assets (increasing and decreasing).

The purpose of the present study was to validate the Adaboost machine learning and probit regression in the prediction of Management's overconfidence at present and in the future. It also compares the predicted models obtained during the years 2012 to 2017. The samples of the research were the companies admitted to the Tehran Stock Exchange, (financial data of 1292 companies/year in total). Data collection in the theoretical part of the study benefitted from the content analysis international research paper in library method and for calculating the data's Excel software was used, and in order to test the research hypotheses, Matlab 2017 and Eviews10.0 were used. The empirical findings demonstrate that The Adaboost's algorithm nonlinear prediction model represents the highest power in learning and prediction (performance of this model) the managerial over-confidence for this year and the following year, proved to be better than the probit regression prediction model.

This paper presents an approach that uses both genetic algorithm (GA) and fuzzy inference system (FIS), for feature selection for descriptor in a quantitative structure activity relationships (QSAR) classification and prediction problem. Unlike the traditional techniques that employed GA, the FIS is used to evaluate an individual population in the GA process. So, the fitness function is introduced and defined by the error rate of the GA and FIS combination. The proposed approach has been implemented and tested using a data set with experimental value anti-human immunodeficiency virus (HIV) molecules. The statistical parameters q2 (leave many out) is equal 0.59 and r (coefficient of correlation) is equal 0.98. These results reveal the capacity for achieving subset of descriptors, with high predictive capacity as well as the effectiveness and robustness of the proposed approach.

In attempts to examine the mapped spaces of a literary narrative, various quantitative approaches have been deployed to extract data from texts to graphs, maps, and trees. Though the existing methods offer invaluable insights, they undertake a rather different project than that of literary scholars who seek to examine privileged or unprivileged representations of certain spaces. This study aims to propose a computerized method to examine how matters of space and spatiality are addressed in literary writings. As the primary source of data, the study will focus on Viet Thanh Nguyen’s The Sympathizer (2015), which explores the lives of Vietnamese diaspora in two geographical locations, Vietnam, and America. To examine the portrayed spatial relations, that is which country is privileged over the other, and to find out the underlying opinion about the two places, this study performs topic modelling with Latent Dirichlet Allocation (LDA) and Latent Semantic Analysis (LSA) by using TextBlob. In addition, Python is used as the analytical tool for this project as it supports two LDA algorithms: Gensim and Mallet. To overcome the limitation that the performance of the model relies on the available libraries in Python, the study employs machine learning approach. Even though the results indicated that both geographical spaces are portrayed slightly positively, America achieves a higher polarity score than Vietnam and hence seems to be the favored space in the novel. This study can assist literary scholars in analyzing spatial relations more accurately in large volumes of works.