Search results

Credit scoring is important for financial institutions in order to accurately predict the likelihood of business failure. Related studies have shown that machine learning techniques, such as neural networks, outperform many statistical approaches to solving this type of problem, and advanced machine learning techniques, such as classifier ensembles and hybrid classifiers, provide better prediction performance than single machine learning based classification techniques. However, it is not known which type of advanced classification technique performs better in terms of financial distress prediction. The paper aims to discuss these issues.

This paper compares neural network ensembles and hybrid neural networks over three benchmarking credit scoring related data sets, which are Australian, German, and Japanese data sets.

The experimental results show that hybrid neural networks and neural network ensembles outperform the single neural network. Although hybrid neural networks perform slightly better than neural network ensembles in terms of predication accuracy and errors with two of the data sets, there is no significant difference between the two types of prediction models.

The originality of this paper is in comparing two types of advanced classification techniques, i.e. hybrid and ensemble learning techniques, in terms of financial distress prediction.

The purpose of this paper is to propose a comprehensive version of a hybrid autoregressive integrated moving average (ARIMA), and artificial neural networks (ANNs) in order to yield a more general and more accurate hybrid model for exchange rates forecasting. For this purpose, the Kalman filter technique is used in the proposed model to preprocess and detect the trend of raw data. It is basically done to reduce the existing noise in the underlying data and better modeling, respectively.

In this paper, ARIMA models are applied to construct a new hybrid model to overcome the above-mentioned limitations of ANNs and to yield a more general and more accurate model than traditional hybrid ARIMA and ANNs models. In our proposed model, a time series is considered as a function of a linear and nonlinear component, so, in the first phase, an ARIMA model is first used to identify and magnify the existing linear structures in data. In the second phase, a multilayer perceptron is used as a nonlinear neural network to model the preprocessed data, in which the existing linear structures are identified and magnified by ARIMA and to predict the future value of time series.

In this paper, a new Kalman filter based hybrid artificial neural network and ARIMA model are proposed as an alternate forecasting technique to the traditional hybrid ARIMA/ANNs models. In the proposed model, similar to the traditional hybrid ARIMA/ANNs models, the unique strengths of ARIMA and ANN in linear and nonlinear modeling are jointly used, aiming to capture different forms of relationship in the data; especially, in complex problems that have both linear and nonlinear correlation structures. However, there are no aforementioned assumptions in the modeling process of the proposed model. Therefore, in the proposed model, in contrast to the traditional hybrid ARIMA/ANNs, it can be generally guaranteed that the performance of the proposed model will not be worse than either of their components used separately. In addition, empirical results in both weekly and daily exchange rate forecasting indicate that the proposed model can be an effective way to improve forecasting accuracy achieved by traditional hybrid ARIMA/ANNs models.

In the proposed model, in contrast to the traditional hybrid ARIMA/ANNs, it can be guaranteed that the performance of the proposed model will not be worse than either of the components used separately. In addition, empirical results in exchange rate forecasting indicate that the proposed model can be an effective way to improve forecasting accuracy achieved by traditional hybrid ARIMA/ANNs models. Therefore, it can be used as an appropriate alternate model for forecasting in exchange ratemarkets, especially when higher forecasting accuracy is needed.

This study aims to investigate how an organic cotton production network learns to maintain its hybrid network and its sustainability in the face of internal and external pressures.

A qualitative case study was conducted in Justa Trama, a Brazilian‐based organic cotton production network formed by six members with different roles and organisational logics.

The study contributes to the literature on hybrid organisations by suggesting that in the case of networks, a compromise strategy is required at the internal level and a manipulation strategy is required at the external level. The network has to learn how to engineer a compromise among internal members and to enforce change among external institutions to maintain its sustainability.

The study was performed in Brazil, a country with serious social and environmental problems. The study thus informs managers of social economy organisations on how to deal with internal and external pressures to maintain their organisation's sustainability as well as policy makers on the importance of these alternative organisations and the importance of specific legislation to stimulate this type of initiative.

The body of research on how hybrid organisations learn to deal with the mutual influence of internal organisational responses and changes in external institutions is limited. Furthermore, this mutual influence has rarely been studied in the context of networks, in which multiple members have to work together to achieve organisational and network‐level objectives as well as to respond to institutional pressures.

New information technologies such as IoT and big data analytics have reshaped the development of smart green products. These products exhibit two important features that are not seen in traditional products: environmental friendliness and data network effect. Based on these unique features, the authors investigate a firm's optimal selling strategy of smart green products from both the profitability and environmental perspectives.

The authors establish stylized models to consider the optimality of three selling strategies: (1) traditional strategy – only offering traditional products, (2) green strategy – only offering smart green products, and (3) hybrid strategy – offering both traditional and smart green products.

The authors’ analysis shows that in the absence of data network effect, there will always be a conflict between profit maximization and environmental protection. However, a strategy that benefits both the firm and the environment exists when data network effect is present. Interestingly, hybrid and traditional strategies can be win-win strategies, but the green strategy cannot. Also surprisingly, the green strategy may harm the environment more as smart products become greener.

This study examines the economic and environmental implications of selling smart green products, and contributes to existing literature on sustainable operations and green product design by incorporating the impact of both consumer environmental awareness and data network effect. The authors’ findings shed light on how to coordinate the profitability and environmental impact of selling smart green products in the era of big data and IoT.

This chapter reviews the conditions leading to the emergence of hybrid network structures involved in public service delivery, analyses opportunities for boundary-spanning by network members and frames these against different manifestations of leadership in such collaborative contexts. It addresses a gap in knowledge around leadership in hybrid networks, on the one hand, and around effectiveness of hybrid networks, on the other hand. Following an in-depth case-study of a hybrid network (local safeguarding children boards, LSCB) in England, UK, we advance a researchable proposition according to which, in turbulent times, the effectiveness of such networks is enhanced through one particular leadership type rather than others.

The purpose of this study is to calculate the effect of different packet sizes 256, 512, 1,024 and 2,048 bytes on a large-scale hybrid network and analysis and identifies which routing protocol is best for application throughput, application delay and network link parameters for different packet sizes. As the routing protocol is used to select the optimal path to transfer data packets from source to destination. It is always important to consider the performance of the routing protocol before the final network configuration. From the literature, it has been observed that RIP (Routing Information Protocol) and OSPF (Open Shortest Path First) are the most popular routing protocols, and it has always been a challenge to select between these routing protocols, especially for hybrid networks. The efficiency of routing protocol mainly depends on resulting throughput and delay. Also, it has been observed that data packet size also plays an essential role in determining the efficiency of routing protocol.

To analyse the effect of different packet sizes using two routing protocols, routing information protocol (RIP) and open shortest path first (OSPF) on the hybrid network, require detailed planning. Designing the network for simulate and then finally analysing the results requires proper study. Each stage needs to be understood well for work accomplishment. Thus, the network’s simulation and evaluation require implementing the proposed work step by step, saving time and cost. Here, the proposed work methodology is defined in six steps or stages.

The simulation results show that both routing protocols – RIP and OSPF are equally good in terms of network throughput for all different packet sizes. However, OSPF performs better in terms of network delay than RIP routing protocol in different packet size scenarios.

In this paper, a fixed network of 125 objects and only RIP and OSPF routing protocol have been used for analysis. Therefore, in the future, a comparison of different network sizes can be considered by increasing or decreasing the number of objects in the proposed network. Furthermore, the other routing protocols can be used for performance evaluation on the same proposed network.

The analysis can be conducted by simulation of the network, enabling us to develop a network environment without restricting the selection of parameters as it minimizes cost, network deployment overhead, human resources, etc. The results are analysed, calculated and compared for each packet size on different routing protocol networks individually and the conclusion is made.

Hybrid systems as the next generation of intelligent applications within the field of mass appraisal and valuation are investigated. Motivated by the obvious limitations of paradigms that are being used in isolation or as stand‐alone techniques such as multiple regression analysis, artificial neural networks and expert systems. Clearly, there are distinct advantages in integrating two or more information processing systems that would address some of the discrete problems of individual techniques. Examines first, the strategic development of mass appraisal approaches which have traditionally been based on “stand‐alone” techniques; second, the potential application of an intelligent hybrid system. Highlights possible solutions by investigating various hybrid systems that may be developed incorporating a nearest neighbour algorithm (k‐NN). The enhancements are aimed at two major deficiencies in traditional distance metrics; user dependence for attribute weights and biases in the distance metric towards matching categorical variables in the retrieval of neighbours. Solutions include statistical techniques: mean, coefficient of variation and significant mean. Data mining paradigms based on a loosely coupled neural network or alternatively a tight coupling with genetic algorithms are used to discover attribute weights. The hybrid architectures developed are applied to a property data set and their performance measured based on their predictive value as well as perspicuity. Concludes by considering the application and the relevance of these techniques within the field of computer assisted mass appraisal.

The purpose of this paper is to analyze the environmental impact of distribution network design.

Typical distribution networks are identified and modeled through interviews with logistics companies in Korea. CO₂ emission is calculated for the distribution network models to evaluate the environmental impact of different network designs. In addition, economic and customer service performances are evaluated to provide realistic and balanced solutions to supply chain managers.

It is suggested that hybrid networks combining Hub-and-Spoke (HS) and Point-to-Point (PP) networks with a small number of sub-terminals are the most effective in both environmental and customer service aspects, whereas HS network is the most cost-effective.

The analysis in this study is based on certain assumptions, and hence full application of these results to specific cases is limited. The combination of PP network with HS network is suggested, forming a hybrid network, and CO₂ mitigation policies need to consider support schemes that can influence a firm’s decision making in relation to network design.

Little attention, however, has been paid to the environmental impact of distribution network design in the exiting literature. This study is a rare attempt at evaluating the environmental impact of distribution network design and may provide valuable implications to policy-makers and practitioners in logistics and manufacturing companies.

A huge variety of devices accumulates as well distributes a large quantity of data either with the help of wired networks or wireless networks to implement a wide variety of application scenarios. The spectrum resources on the other hand become extremely unavailable with the development of communication devices and thereby making it difficult to transmit data on time.

The spectrum resources on the other hand become extremely unavailable with the development of communication devices and thereby making it difficult to transmit data on time. Therefore, the technology of cognitive radio (CR) is considered as one of the efficient solutions for addressing the drawbacks of spectrum distribution whereas the secondary user (SU) performance is significantly influenced by the spatiotemporal instability of spectrum.

As a result, the technique of the hybrid filter detection network model (HFDNM) is suggested in this research work under various SU relationships in the networks of CR. Furthermore, a technique of hybrid filter detection was recommended in this work to enhance the performance of idle spectrum applications. When compared to other existing techniques, the suggested research work achieves enhanced efficiency with respect to both throughputs as well as delay.

The proposed HFDNM improved the transmission delay at 3 SUs with 0.004 s/message and 0.008 s/message when compared with existing NCNC and NNC methods in case of number of SUs and also improved 0.02 s/message and 0.08 s/message when compared with the existing methods of NCNC and NNC in case of channel loss probability at 0.3.

This study constructs time series model, artificial neural networks (ANNs) and statistical topologies to examine the volatility and forecast foreign exchange rates. The Mauritian forex market has been utilized as a case study, and daily data for nominal spot rate (during a time period of five years spanning from 2014 to 2018) for EUR/MUR, GBP/MUR, CAD/MUR and AUD/MUR have been applied for the predictions.

Autoregressive integrated moving average (ARIMA) and generalized autoregressive conditional heteroskedasticity (GARCH) models are used as a basis for time series modelling for the analysis, along with the non-linear autoregressive network with exogenous inputs (NARX) neural network backpropagation algorithm utilizing different training functions, namely, Levenberg–Marquardt (LM), Bayesian regularization and scaled conjugate gradient (SCG) algorithms. The study also features a hybrid kernel principal component analysis (KPCA) using the support vector regression (SVR) algorithm as an additional statistical tool to conduct financial market forecasting modelling. Mean squared error (MSE) and root mean square error (RMSE) are employed as indicators for the performance of the models.

The results demonstrated that the GARCH model performed better in terms of volatility clustering and prediction compared to the ARIMA model. On the other hand, the NARX model indicated that LM and Bayesian regularization training algorithms are the most appropriate method of forecasting the different currency exchange rates as the MSE and RMSE seemed to be the lowest error compared to the other training functions. Meanwhile, the results reported that NARX and KPCA–SVR topologies outperformed the linear time series models due to the theory based on the structural risk minimization principle. Finally, the comparison between the NARX model and KPCA–SVR illustrated that the NARX model outperformed the statistical prediction model. Overall, the study deduced that the NARX topology achieves better prediction performance results compared to time series and statistical parameters.

The foreign exchange market is considered to be instable owing to uncertainties in the economic environment of any country and thus, accurate forecasting of foreign exchange rates is crucial for any foreign exchange activity. The study has an important economic implication as it will help researchers, investors, traders, speculators and financial analysts, users of financial news in banking and financial institutions, money changers, non-banking financial companies and stock exchange institutions in Mauritius to take investment decisions in terms of international portfolios. Moreover, currency rates instability might raise transaction costs and diminish the returns in terms of international trade. Exchange rate volatility raises the need to implement a highly organized risk management measures so as to disclose future trend and movement of the foreign currencies which could act as an essential guidance for foreign exchange participants. By this way, they will be more alert before conducting any forex transactions including hedging, asset pricing or any speculation activity, take corrective actions, thus preventing them from making any potential losses in the future and gain more profit.

This is one of the first studies applying artificial intelligence (AI) while making use of time series modelling, the NARX neural network backpropagation algorithm and hybrid KPCA–SVR to predict forex using multiple currencies in the foreign exchange market in Mauritius.