Search results

The purpose of this paper is to demonstrate the applicability of swarm and evolutionary techniques for regularized machine learning. Generally, by defining a proper penalty function, regularization laws are embedded into the structure of common least square solutions to increase the numerical stability, sparsity, accuracy and robustness of regression weights. Several regularization techniques have been proposed so far which have their own advantages and disadvantages. Several efforts have been made to find fast and accurate deterministic solvers to handle those regularization techniques. However, the proposed numerical and deterministic approaches need certain knowledge of mathematical programming, and also do not guarantee the global optimality of the obtained solution. In this research, the authors propose the use of constraint swarm and evolutionary techniques to cope with demanding requirements of regularized extreme learning machine (ELM).

To implement the required tools for comparative numerical study, three steps are taken. The considered algorithms contain both classical and swarm and evolutionary approaches. For the classical regularization techniques, Lasso regularization, Tikhonov regularization, cascade Lasso-Tikhonov regularization, and elastic net are considered. For swarm and evolutionary-based regularization, an efficient constraint handling technique known as self-adaptive penalty function constraint handling is considered, and its algorithmic structure is modified so that it can efficiently perform the regularized learning. Several well-known metaheuristics are considered to check the generalization capability of the proposed scheme. To test the efficacy of the proposed constraint evolutionary-based regularization technique, a wide range of regression problems are used. Besides, the proposed framework is applied to a real-life identification problem, i.e. identifying the dominant factors affecting the hydrocarbon emissions of an automotive engine, for further assurance on the performance of the proposed scheme.

Through extensive numerical study, it is observed that the proposed scheme can be easily used for regularized machine learning. It is indicated that by defining a proper objective function and considering an appropriate penalty function, near global optimum values of regressors can be easily obtained. The results attest the high potentials of swarm and evolutionary techniques for fast, accurate and robust regularized machine learning.

The originality of the research paper lies behind the use of a novel constraint metaheuristic computing scheme which can be used for effective regularized optimally pruned extreme learning machine (OP-ELM). The self-adaption of the proposed method alleviates the user from the knowledge of the underlying system, and also increases the degree of the automation of OP-ELM. Besides, by using different types of metaheuristics, it is demonstrated that the proposed methodology is a general flexible scheme, and can be combined with different types of swarm and evolutionary-based optimization techniques to form a regularized machine learning approach.

The authors develop a framework to build an early warning mechanism in detecting financial deterioration of Chinese companies. Many studies in the financial distress and bankruptcy prediction literature rarely do they examine the impact of pre-processing financial indicators on the prediction performance. The purpose of this paper is to address this shortcoming.

The proposed framework is evaluated by using both original and discretized data, and a least absolute shrinkage and selection operator (LASSO) selection technique for choosing an appropriate subset of financial ratios for improved predictive performance. The financial ratios are then analyzed by five different data mining techniques. Managerial insights, using data from Chinese companies, are revealed by the methodology employed.

The prediction accuracy increases after we discretized the continuous variables of financial ratios. A better prediction performance can be achieved by including fewer, but relatively more significant variables. Random forest has the highest overall performance following closely by SVM and neural network.

The contribution of this study is fourfold. First, the authors add to the literature on defaults by showing variable discretization to be an essential pre-processing step to improve the prediction performance for classification problems. Second, the authors demonstrate that machine learning approaches can achieve better performance than traditional statistical methods in classification tasks. Third, the authors provide the evidence for the adoption of C5.0 over other methods because rules generated with C5.0 provide managerial insights for managers. Finally, the authors demonstrate the effectiveness of the LASSO technique for identifying the most important financial ratios from each category, enabling one to build better predictive models.

The purpose of this paper is to apply various data mining techniques for predicting the financial performance of Islamic banking in Indonesia through the main exogenous determinants of profitability by choosing the best data mining technique based on the criteria of the highest accuracy score of testing and training.

This paper used data mining techniques to predict the financial performance of Islamic banking by applying all of LASSO regression, random forest (RF), artificial neural networks and k-nearest neighbor (KNN) over monthly data sets of all the full-fledged Islamic banks working in Indonesia from January 2011 until March 2020. This study used return on assets as a real measurement of financial performance, whereas the capital adequacy ratio, asset quality and liquidity management were used as exogenous determinants of financial performance.

The experimental results showed that the optimal task for predicting the financial performance of Islamic banking in Indonesia is the KNN technique, which affords the best-predicting accuracy, and gives the optimal knowledge from the financial performance of Islamic banking determinants in Indonesia. As well, the RF provides closer values to the optimal accuracy of the KNN, which makes it another robust technique in predicting the financial performance of Islamic banking.

This paper restricted modeling the financial performance of Islamic banking to profitability through the main determinants of return of assets in Indonesia. Future research could consider enlarging the modeling of financial performance using other models such as CAMELS and Z-Score to predict the financial performance of Islamic banking under data mining techniques.

Owing to the lack of using data mining techniques in the Islamic banking sector, this paper would fill the literature gap by providing new effective techniques for predicting financial performance in the Islamic banking sector using data mining approaches, which can be efficient tools in business and management modeling for financial researchers and decision-makers in the Islamic banking sector.

According to the author’s knowledge, this paper is the first that provides data mining techniques for predicting the financial performance of the Islamic banking sector in Indonesia.

The current study aims to analyze the linkage among bank competition, liquidity and loan price in an interconnected bank network system.

The study employs the Lerner index to estimate bank power; Granger non-causality for estimating competition, liquidity and loan price network structure; principal component for developing competition network index, liquidity network index and price network index; and panel VAR and LASSO-VAR for analyzing the dynamics of interactive network effect. Current work considers 33 Indian banks, and the duration of the study is from 2010 to 2020.

Network structures are concentrated during the economic upcycle and dispersed during the economic downcycle. A significant interaction among bank competition, liquidity and loan price networks exists in the Indian banking system.

The study meaningfully contributes to the existing literature by adding new insights concerning the interrelationship between bank competition, loan price and bank liquidity networks. While enhancing competition in the banking system, the regulator should also pay attention toward making liquidity provisions. The interactive network framework provides direction to the regulator to formulate appropriate policies for managing competition and liquidity while ensuring the solvency and stability of the banking system.

The study contributes to the limited literature concerning interactive relationship among bank competition, liquidity and loan price in the Indian banks.

The main purpose of this study is to forecast inflation rates in the case of the Turkish economy with shrinkage methods of machine learning algorithms.

This paper compares the predictive ability of a set of machine learning techniques (ridge, lasso, ada lasso and elastic net) and a group of benchmark specifications (autoregressive integrated moving average (ARIMA) and multivariate vector autoregression (VAR) models) on the extensive dataset.

Results suggest that shrinkage methods perform better for variable selection. It is also seen that lasso and elastic net algorithms outperform conventional econometric methods in the case of Turkish inflation. These algorithms choose the energy production variables, construction-sector measure, reel effective exchange rate and money market indicators as the most relevant variables for inflation forecasting.

Turkish economy that is a typical emerging country has experienced two digit and high volatile inflation regime starting with the year 2017. This study contributes to the literature by introducing the machine learning techniques to forecast inflation in the Turkish economy. The study also compares the relative performance of machine learning techniques and different conventional methods to predict inflation in the Turkish economy and provide the empirical methodology offering the best predictive performance among their counterparts.

Internet of Things (IoT) is a network, which provides the connection with various physical objects such as smart machines, smart home appliance and so on. The physical objects are allocated with a unique internet address, namely, Internet Protocol, which is used to perform the data broadcasting with the external objects using the internet. The sudden increment in the number of attacks generated by intruders, causes security-related problems in IoT devices while performing the communication. The main purpose of this paper is to develop an effective attack detection to enhance the robustness against the attackers in IoT.

In this research, the lasso regression algorithm is proposed along with ensemble classifier for identifying the IoT attacks. The lasso algorithm is used for the process of feature selection that modeled fewer parameters for the sparse models. The type of regression is analyzed for showing higher levels when certain parts of model selection is needed for parameter elimination. The lasso regression obtains the subset for predictors to lower the prediction error with respect to the quantitative response variable. The lasso does not impose a constraint for modeling the parameters caused the coefficients with some variables shrink as zero. The selected features are classified by using an ensemble classifier, that is important for linear and nonlinear types of data in the dataset, and the models are combined for handling these data types.

The lasso regression with ensemble classifier–based attack classification comprises distributed denial-of-service and Mirai botnet attacks which achieved an improved accuracy of 99.981% than the conventional deep neural network (DNN) methods.

Here, an efficient lasso regression algorithm is developed for extracting the features to perform the network anomaly detection using ensemble classifier.

Despite rising incomes and reduction of extreme poverty, the feeling of being poor remains widespread. Support programs can improve well-being, but they first require identifying who are the households that judge their income is insufficient to meet their basic needs, and what factors are associated with subjective poverty.

Households report the income level they judge is sufficient to make ends meet. Then, they are classified as being subjectively poor if their own monetary income is inferior to the level they indicated. Second, the study compares the performance of three machine learning algorithms, the random forest, support vector machines and least absolute shrinkage and selection operator (LASSO) regression, applied to a set of socioeconomic variables to predict subjective poverty status.

The random forest generates 85.29% of correct predictions using a range of income and non-income predictors, closely followed by the other two techniques. For the middle-income group, the LASSO regression outperforms random forest. Subjective poverty is mostly associated with monetary income for low-income households. However, a combination of low income, low endowment (land, consumption assets) and unusual large expenditure (medical, gifts) constitutes the key predictors of feeling poor for the middle-income households.

To reduce the feeling of poverty, policy intervention should continue to focus on increasing incomes. However, improvements in nonincome domains such as health expenditure, education and family demographics can also relieve the feeling of income inadequacy. Methodologically, better performance of either algorithm depends on the data at hand.

For the first time, the authors show that prediction techniques are reliable to identify subjective poverty prevalence, with example from rural China. The analysis offers specific attention to the modest-income households, who may feel poor but not be identified as such by objective poverty lines, and is relevant when policy-makers seek to address the “next step” after ending extreme poverty. Prediction performance and mechanisms for three machine learning algorithms are compared.

In accounting and finance, researchers have used many ways to detect manager’s fraud risk. Until now, many researchers have used some data mining methods in these two fields to detect this risk. The purpose of this paper is to compare the precision of two data mining methods in detecting such a risk.

For this purpose, this paper analyzed the texts of board’s reports and used two methods including the convex optimization (CVX) method and least absolute shrinkage and selection operator (LASSO) regression method. In this way, the words of these reports, which have the greatest power in explaining the manager’s high fraud risk index, were identified. Using these words, this paper presented a model that could detect manager’s high fraud risk index in companies.

The results indicated that both methods can detect the manager’s high fraud risk index with a precision between 82.55 and 91.25 percent. The LASSO method was significantly more precise than the CVX method.

The lack of access to an official and reliable list of firms suspected to fraud and the lack of access to the Microsoft Word (MS Word) file of board’s reports were two of the most important limitations of this study.

Regulatory bodies and independent auditors can consider the proposed methods in this study for assessing the fraud risk for a firm or other legal parties.

This paper avoided using merely financial statements data to detect the manager’s fraud risk index and focused on texts of board’s reports for the detection process. The capabilities of data mining and text mining methods for detecting the manager’s fraud risk index using board’s reports were tested in this paper. By comparing CVX and LASSO results, this paper indicated that methods with a binary-dependent variable have more power and are more precise than methods with continuous-dependent variables for detecting fraud.

This study aims to analyze the influence of firm characteristics in dividend payout in a concentrated ownership setting.

This study is probably the first to use the lasso technique for model selection and error prediction in the study of dividend payout in India. The lasso method comprises subsampling the available data set and performing reiterative regressions on those samples to generate the model with the best fit. This study incorporates four different ways of performing lasso treatment to get the best fit among them.

This study analyzes the influence of firm characteristics on dividend payout in the Indian context and asserts that firms with growth potential and earnings volatility do not hesitate to cut dividends. This study does not find evidence for signaling, agency cost and life cycle theories in a concentrated ownership setting. Earnings is the single most important factor to have a positive influence on dividend, while excessively leveraged firms are restrictive of dividend payout. Taxation has a prominent role in altering the way firms pay dividend.

The recent changes in buyback taxation offer another opportunity to test the reactive behavior of firms. Also, given the disregard for traditional motivations, further research needs to be done to determine if dividend adjustments (on the lower side) help enhance firm value or not.

This study may help investors view dividends in a proper perspective. Firms give importance to investments over dividends and thus investors need not dwell on dividend changes if firms fulfill their growth potential.

It lends perspective to investors about dividend changes and its importance.

The methodology used for analysis is absolutely original in the literature pertaining to dividend policy in the Indian context. The literature is abundant with theories advocating or opposing the eminence of dividend payout; however, this study takes a holistic view of all influential dividend determinants in literature to understand dividend payout.

The Health Sector Evolution Plan (HSEP) is the most recent reform in Iran’s health care system that was launched in May 2014 in all university-affiliated hospitals to reduce health care expenditure for patients, while improving the efficiency and quality of hospital services. The purpose of this paper is to evaluate the impact of the HSEP on the performance of 15 hospitals affiliated with Kermanshah University of Medical Sciences (KUMS), located in the western region of Iran.

The Pabon Lasso model was used to measure the performance of hospitals before and after the implementation of the HSEP in 2013-2014 and 2015-2016, respectively. Three indicators of average length of stay (ALoS), bed occupancy rate (BOR) and bed turnover rate (BTR) were analyzed by the Pabon Lasso model.

The results showed that the average ALoS, BTR and BOR before the introduction of the HSEP were 2.59 days, 92 times and 57 percent, respectively, and the corresponding figures for these indicators after the implementation of the HSEP were 2.61 days, 98.9 times and 59.9 percent. The results indicated that before the introduction of the HESP, 40 percent of hospitals were in zone 1 (poor performance: low BTR and BOR and high ALoS), 27 percent in zone 2, 20 percent in zone 3 (good performance: high BTR and BOR and low ALoS) and 13 percent in zone 4. After the HSEP, the proportion of hospitals in zones 1-4 was 33, 27, 20 and 20 percent, respectively.

This study is the first to use the Pabon Lasso model technique to evaluate the impact of the HSEP on hospitals affiliated with KUMS.