External Two Stage DEA Analysis of Bank Efficiency in West Balkan Countries

Since the beginning of the application of the Data Envelopment Analysis (DEA) model in various areas of the economy, it has found its wide application in the field of finance, more specifically banks, in the last few years. The focus of this research was to determine the sustainability of the intermediate function of banks, especially in recent years when interest rates on deposits have been at a minimum level. The research was divided into two parts, wherein the first part determined the efficiency of the intermediate function of banks in the countries of the Western Balkans in the period from 2015 to 2019. The second part approached the regression analysis in which we determined the influence of the bank size, type of bank, and mergers and acquisitions (M&A) activity on the defined efficiency. In the first stage we applied the output-oriented DEA model using deposits, labor costs, and capital as input variables; on the other side, we used loans and investments as output variables. We used data from the revised financial statements of the banks operating in Serbia, Bosnia and Herzegovina, Montenegro, North Macedonia, and Albania. The results of our study showed that there is a difference in efficiency levels between countries and within countries in the considered time period. Furthermore, Tobit regression analysis showed a significant and negative influence of the bank type and M&A on relative technical efficiency of banks, and a positive and significant relationship between bank size and relative efficiency. These findings suggest that large commercial banks can sustain on the West Balkan market. It is to be expected that less efficient small banks will be taken over by large and more efficient banks.

Increasing the mechanical properties of structural cast iron for machine-building parts by combined Mn – Al alloying

The object of research in this work was cast iron for machine-building parts, alloyed with Al. The possibility of improving the mechanical properties of cast iron by choosing the optimal Mn – Al combinations, depending on the carbon content in the cast iron, was determined. The study was carried out on the basis of available retrospective data of serial industrial melts by constructing the regression equation for the ultimate strength of cast iron in the three-factor space of the input variables C – Mn – Al. The optimization problem was solved by the ridge analysis method after reducing the dimension of the factor space by fixing the carbon content at three levels: C = 3 %, C = 3.3 %, and C = 3.6 %. It was found that the maximum values of the ultimate strength are achieved at the minimum level of carbon content (C = 3%) and are in the range of values close to 300 MPa. In this case, the Al content is in the range (2.4–2.6) %, and the Mn content is about 0.82 %. With an increase in the carbon content, there is a tendency to a decrease in the content of Mn and Al in the alloy, which is necessary to ensure the ultimate strength close to 300 MPa. The results of the ridge analysis of the response surface also showed that at the upper limit of the carbon content (C = 3.6%), it is not possible to reach the ultimate strength of 300 MPa in the existing range of Mn and Al variation. All solutions are verified for the following ranges of input variables C = (2.94–3.66) %, Mn = (0.5–1.1) %, Al = (1.7–2.9) %. Graphical-analytical descriptions of the optimal Mn – Al ratios are obtained, depending on the actual content of carbon in the alloy, which make it possible to purposefully select the optimal melting modes by controlling the tensile strength of the alloy

Areal Precipitation Coverage Ratio for Enhanced AI Modelling of Monthly Runoff: A New Satellite Data-Driven Scheme for Semi-Arid Mountainous Climate

Satellite remote sensing provides useful gridded data for the conceptual modelling of hydrological processes such as precipitation–runoff relationship. Structurally flexible and computationally advanced AI-assisted data-driven (DD) models foster these applications. However, without linking concepts between variables from many grids, the DD models can be too large to be calibrated efficiently. Therefore, effectively formulized, collective input variables and robust verification of the calibrated models are desired to leverage satellite data for the strategic DD modelling of catchment runoff. This study formulates new satellite-based input variables, namely, catchment- and event-specific areal precipitation coverage ratios (CCOVs and ECOVs, respectively) from the Global Precipitation Mission (GPM) and evaluates their usefulness for monthly runoff modelling from five mountainous Karkheh sub-catchments of 5000–43,000 km2 size in west Iran. Accordingly, 12 different input combinations from GPM and MODIS products were introduced to a generalized deep learning scheme using artificial neural networks (ANNs). Using an adjusted five-fold cross-validation process, 420 different ANN configurations per fold choice and 10 different random initial parameterizations per configuration were tested. Runoff estimates from five hybrid models, each an average of six top-ranked ANNs based on six statistical criteria in calibration, indicated obvious improvements for all sub-catchments using the new variables. Particularly, ECOVs were most efficient for the most challenging sub-catchment, Kashkan, having the highest spacetime precipitation variability. However, better performance criteria were found for sub-catchments with lower precipitation variability. The modelling performance for Kashkan indicated a higher dependency on data partitioning, suggesting that long-term data representativity is important for modelling reliability.

HobPre: accurate prediction of human oral bioavailability for small molecules

Human oral bioavailability (HOB) is a key factor in determining the fate of new drugs in clinical trials. HOB is conventionally measured using expensive and time-consuming experimental tests. The use of computational models to evaluate HOB before the synthesis of new drugs will be beneficial to the drug development process. In this study, a total of 1588 drug molecules with HOB data were collected from the literature for the development of a classifying model that uses the consensus predictions of five random forest models. The consensus model shows excellent prediction accuracies on two independent test sets with two cutoffs of 20% and 50% for classification of molecules. The analysis of the importance of the input variables allowed the identification of the main molecular descriptors that affect the HOB class value. The model is available as a web server at www.icdrug.com/ICDrug/ADMET for quick assessment of oral bioavailability for small molecules. The results from this study provide an accurate and easy-to-use tool for screening of drug candidates based on HOB, which may be used to reduce the risk of failure in late stage of drug development. Graphical Abstract

Demand Side Financing and Healthcare Seeking of Pregnant Women

Demand-side financing (DSF) scheme is popularly known as the maternal health voucher program, which is launched in many developing countries of the world including Bangladesh as an intervention of developing overall health status. Maternal mortality ratio is a strong indicator of health profile of any country and pregnant women are prone to fall vulnerable situation. This review was aimed to find gap/missing of existing literature in order to make foundation of new research on healthcare seeking of pregnant women along with financing coverage. After repeated critical review of number original articles, some gaps have been found. Almost every article they focused on outcome and mildly highlighted input variables but did not consider all possible variables and missed to show interlink between those variables.

Prediction of Water Level Using Time Series, Wavelet and Neural Network Approaches

To control water resources in many domains such as agriculture, flood forecasting, and hydro-electrical dams, forecasting water level needs to predict. In this article, a new computational approach using a data driven model and time series is proposed to calculate the forecast water level in short time. Concretely, wavelet-artificial neural network (WAANN) and time series (TS) are combined together called WAANN-TS that encourages the advantage of each model. For this real time project work, Yen Bai station, Northwest Vietnam was chosen as an experimental case study to apply the proposed model. Input variables into the Wavelet-ANN structure is water level data. Time series and ANN models are built, and their performances are compared. The results indicate the greater accuracy of the proposed models at Hanoi station. The final proposal WAANN−TS for water level forecasting shows good performance with root mean square error (RMSE) from 10−10 to 10−11.

Bayesian optimization with partially specified queries

Bayesian optimization (BO) is an approach to optimizing an expensive-to-evaluate black-box function and sequentially determines the values of input variables to evaluate the function. However, it is expensive and in some cases becomes difficult to specify values for all input variables, for example, in outsourcing scenarios where production of input queries with many input variables involves significant cost. In this paper, we propose a novel Gaussian process bandit problem, BO with partially specified queries (BOPSQ). In BOPSQ, unlike the standard BO setting, a learner specifies only the values of some input variables, and the values of the unspecified input variables are randomly determined according to a known or unknown distribution. We propose two algorithms based on posterior sampling for cases of known and unknown input distributions. We further derive their regret bounds that are sublinear for popular kernels. We demonstrate the effectiveness of the proposed algorithms using test functions and real-world datasets.

Optimal Solution of Combined Heat and Power Dispatch Problem Using Whale Optimization Algorithm

In this article whale optimization algorithm (WOA) has been applied to solve the combined heat and power economic dispatch (CHPED) problem. The CHPED is energy system which provides both heat and power. Due to presence of valve point loading and the prohibited working region, the CHPED problems become more complex one. The main objective of CHPED problem is to minimize the total cost of fuel as well as heat with fulfill the load demand. This optimization technique shows several advantages like having few input variables, best quality of solution with rapid computational time. The recommended approach is carried out on three test systems. The simulation results of the present work certify the activeness of the proposed technique.

Eficiência das Ferrovias Especializadas em Transporte de Minério de Ferro e Pelotas

ABSTRACT Objective: the objective is to compare the relative efficiency of the railways specialized in transporting iron ore (MFe) and pellets (PLMFe), which are part of the assets of mining companies and pellet plants considering the 2016 scenario. Methods: the methods used were the data envelopment analysis (DEA) technique, with the application of the output-oriented constant returns scale (CRS) model; the initial combinatorial multicriteria method for choosing the input variables; and Tobit regression as a validation strategy for the DEA model. Results: of the twelve railways evaluated, three railways were identified as efficient: Estrada de Ferro Carajás, Fortescue, and Mount Newman. Conclusions: the applied model was considered a good method to evaluate the efficiency of railways specialized in transporting MFe and PLMFe, as it determined the efficiency of each railway, suggesting the necessary increase in the output variable or adjustments in the input variables so that the railways reach the efficiency frontier. With that, companies can use the results of this study to guide future improvements to make their railways more efficient or maintain them on the frontier of efficiency.

An Approach Combining DEA and ANN for Hotel Performance Evaluation

For a hotel to succeed in the long run, it becomes vital to achieve higher profits along with increased performance. The performance evaluation of a hotel can signify its sustainable competitiveness within the hospitality industry. This article performs a two-stage study that combines data envelopment analysis (DEA) and artificial neural network (ANN) to evaluate hotel performance. The first stage to evaluate the efficiency for hotels is by using the DEA technique. The input variables considered are the number of rooms and the ratings corresponding to six aspects of a hotel (service, room, value, location, sleep quality, and cleanliness). Also, revenue per available room (RevPAR) and customer satisfaction (CS) are the output variables. The distinguishing factor of this article is that it involves the use of EWOM for performance evaluation. In the second stage, the performance of the hotels is judged by using the ANN technique. The ANN results showed that the performance of the hotels is quite good. Finally, discussions based on the results and scope for future studies are provided.