Search

Deep neural network (DNN) architectures such as recurrent neural networks and transformers display outstanding performance in modeling sequential unstructured data. However, little is known about their merit to model customer churn with time-varying data. The paper provides a comprehensive evaluation of the ability of recurrent neural networks and transformers for customer churn prediction (CCP) using time-varying behavioral features in the form of recency, frequency, and monetary value (RFM). RFM variables are the backbone of CCP and, more generally, customer behavior forecasting. We examine alternative strategies for integrating time-varying and non-variant customer features in one network architecture. In this scope, we also assess hybrid approaches that incorporate the outputs of DNNs in conventional CCP models. Using a comprehensive panel data set from a large financial services company, we find recurrent neural networks to outperform transformer architectures when focusing on time-varying RFM features. This finding is confirmed when time-invariant customer features are included, independent of the specific form of feature integration. Finally, we find no statistical evidence that hybrid approaches (based on regularized logistic regression and extreme gradient boosting) improve predictive performance—highlighting that DNNs and especially recurrent neural networks are suitable standalone classifiers for CCP using time-varying RFM measures. [ABSTRACT FROM AUTHOR]

Every contact centre engages in some form of Call Quality Monitoring in order to improve agent performance and customer satisfaction. Call centres have traditionally used a manual process to sort, select, and analyse a representative sample of interactions for evaluation purposes. Unfortunately, such a process is marked by subjectivity, which in turn results in a distorted picture of agent performance. To address the challenge of identifying and removing subjectivity, empirical research is required. In this paper, we introduce an evidence-based, machine learning-driven framework for the automatic detection of subjective calls. We analyse a corpus of seven hours of recorded calls from a real-estate call centre using Deep Neural Network (DNN) for a multi-classification problem. The study establishes the first baseline for subjectivity detection, with an accuracy of 75%, which is comparable to relevant speech studies in emotional recognition and performance classification. We conclude, among other things, that in order to achieve the best performance evaluation, subjective calls should be removed from the evaluation process or subjective scores deducted from the overall results. [ABSTRACT FROM AUTHOR]

One of the significant challenges in the sports industry is identifying the factors influencing match results and their respective weightage. For appropriate recommendations to the team management and the team players, there is a need to predict the match and quantify the important factors for which prediction models need to be developed. The second thing required is identifying talented and emerging players and performing an associative analysis of the important factors to the match-winning outcome. This paper formulates a hybrid machine learning-clustering-associative rules model. This paper also implements the framework for cricket matches, one of the most popular sports globally watched by billions around the world. We predict the match outcome for One day Internationals (ODIs) and Twenty 20 s (T20s) (two formats of Cricket representing fifty over and twenty over versions respectively) adopting state-of-the-art machine learning algorithms, Random Forest, Gradient Boosting, and Deep neural networks. The variable importance is computed using machine-learning techniques and further statistically validated through the regression model. The emerging talented players are identified by clustering. Association rules are generated for determining the best possible winning outcome. The results show that environmental conditions are equally crucial for determining a match result, as are internal quantitative factors. The model is thus helpful for both team management and for players to improve their winning strategy and also for discovering emerging players to form an unbeatable team. [ABSTRACT FROM AUTHOR]

The article discusses various reports published within the issue, including one by Zhou et al on the cyclic scheduling problem for electroplating lines and another by Agarwal on justification for the augmented-neural-network approach.

The paper investigates hyperparameter optimization problem. Hyperparameters are the parameters of model parameter distribution. The adequate choice of hyperparameter values prevents model overfit and allows it to obtain higher predictive performance. Neural network models with large amount of hyperparameters are analyzed. The hyperparameter optimization for models is computationally expensive. The paper proposes modifications of various gradient-based methods to simultaneously optimize many hyperparameters. The paper compares the experiment results with the random search. The main impact of the paper is hyperparameter optimization algorithms analysis for the models with high amount of parameters. To select precise and stable models the authors suggest to use two model selection criteria: cross-validation and evidence lower bound. The experiments show that the models optimized using the evidence lower bound give higher error rate than the models obtained using cross-validation. These models also show greater stability when data is noisy. The evidence lower bound usage is preferable when the model tends to overfit or when the cross-validation is computationally expensive. The algorithms are evaluated on regression and classification datasets. [ABSTRACT FROM AUTHOR]

The returns on most financial assets exhibit kurtosis and many also have probability distributions that possess skewness as well. In this paper a general multivariate model for the probability distribution of assets returns, which incorporates both kurtosis and skewness, is described. It is based on the multivariate extended skew-Student- t distribution. Salient features of the distribution are described and these are applied to the task of asset pricing. The paper shows that the market model is non-linear in general and that the sensitivity of asset returns to return on the market portfolio is not the same as the conventional beta, although this measure does arise in special cases. It is shown that the variance of asset returns is time varying and depends on the squared deviation of market portfolio return from its location parameter. The first order conditions for portfolio selection are described. Expected utility maximisers will select portfolios from an efficient surface, which is an analogue of the familiar mean-variance frontier, and which may be implemented using quadratic programming. [ABSTRACT FROM AUTHOR]

The existence of contaminants in metal alloys products is the main problem affecting the product quality, which is an important requirement for competitiveness in industries. This paper proposes the application of a relevance vector machine for regression (RVR) and a support vector machine for regression (SVR) optimized by a self-adaptive differential evolution algorithm for regression to model the phosphorus concentration levels in a steelmaking process based on actual data. In general, the appropriate choice of learning hyperparameters is a crucial step in obtaining a well-tuned RVM and SVM. To address this issue, we apply a self-adaptive differential evolution algorithm, which is an evolutionary algorithm for global optimization. We compare the performance of the RVR and SVR models with the ridge regression, multiple linear regression, model trees, artificial neural network, and random vector functional link neural network models. RVR and SVR models have smaller RMSE values and better performance than the other models. Our study indicates that the RVR and SVR models are adequate tools for predicting the phosphorus concentration levels in the steelmaking process. [ABSTRACT FROM AUTHOR]

Artificial Intelligence (AI) is critical for data-driven decision making to increase resource utilization, operational performance, and service quality in various industry domains, particularly in healthcare. Using AI in healthcare operations can significantly improve treatment outcomes and enhance patient satisfaction while reducing costs. In this paper, we propose a multi-stage framework to build an AI-based decision support tool that can predict the 5-year survivability of lung cancer patients. We evaluate the proposed framework using the Surveillance, Epidemiology, and End Results dataset pertaining to the 1973–2015 period obtained from the National Institutes of Health. The first stage entails data preprocessing and target creation. The second stage applies six AI algorithms with feature selection through Particle Swarm Optimization and hyperparameter tuning with Cross-Validation. These Algorithms include Logistic Regression, Decision Trees, Random Forests (RF), Adaptive Boosting (AdaBoost), Artificial Neural Network, and Naïve Bayes. The results show that RF and AdaBoost models yield an AUC rate of 0.94 and outperform the other models. Stage 3 utilizes permutation importance to interpret the RF and AdaBoost models and applies Tree-based Augmented Naïve Bayes to gain insights regarding the interrelations among important features. The results of Stage 3 delineate that the number of lymph nodes containing metastases), the number of tumors that patients have had in their lifetime, the patient's age, and the microscopic composition of cells rank among the topmost important features and can significantly impact patient survivability. We think this study has significant practical implications in helping physicians predict prognosis and develop treatment plans for lung cancer patients. [ABSTRACT FROM AUTHOR]

A sustainability program is about implementing essential sustainability practices at various intensities that will not harm people because of firm actions. This paper formulates an optimization model to identify an optimal intensity of implementation of selected sustainability practices referred as sustainability program for maximising manufacturing industry sustainability performance for a known set of budgetary and minimum thresholds constraints with respect to economic, social and socio-economic criteria. Besides modelling the paper proposes a random search procedure embedding the NN to determine the optimal sustainability program and explains the usefulness with a sample problem. Sensitivity analysis is carried out to understand the behaviour of the model. It is observed that the sustainability performances depend on the constraints such as budget limitation and threshold values of performance criterion. [ABSTRACT FROM AUTHOR]

This paper reports the results obtained from use of project complexity parameters in modeling effort estimates. It highlights the attention that complexity has recently received in the project management area. After considering that traditional knowledge has consistently proved to be prone to failure when put into practice on actual projects, the paper endorses the belief that there is a need for more open-minded and novel approaches to project management. With a view to providing some insight into the opportunities that integrate complexity concepts into model building offers, we extend the work previously undertaken on the complexity dimension in project management. We do so analyzing the results obtained with classical linear models and artificial neural networks when complexity is considered as another managerial parameter. For that purpose, we have used the International Software Benchmarking Standards Group data set. The results obtained proved the benefits of integrating the complexity of the projects at hand into the models. They also addressed the need of a complex system, such as artificial neural networks, to capture the fine nuances of the complex systems to be modeled, the projects. [ABSTRACT FROM AUTHOR]

Given the NP-Hard nature of many optimization problems, it is often impractical to obtain optimal solutions to large-scale problems in reasonable computing time. For this reason, heuristic and metaheuristic search approaches are used to obtain good solutions fast. However, these techniques often struggle to develop a good balance between local and global search. In this paper we propose a hybrid metaheuristic approach which we call the NeuroGenetic approach to search for good solutions for these large scale optimization problems by at least partially overcoming this challenge. The proposed NeuroGenetic approach combines the Augmented Neural Network (AugNN) and the Genetic Algorithm (GA) search approaches by interleaving the two. We chose these two approaches to hybridize, as they offer complementary advantages and disadvantages; GAs are very good at searching globally, while AugNNs are more proficient at searching locally. The proposed hybrid strategy capitalizes on the strong points of each approach while avoiding their shortcomings. In the paper we discuss the issues associated with the feasibility of hybridizing these two approaches and propose an interleaving algorithm. We also provide empirical evidence demonstrating the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

An efficient and effective logistic system is a strategic objective in any productive business. This paper presents a real case study of a routing problem in a food industry firm. This problem is solved as a Vehicle Routing Problem (VRP) using the Neural Network (NN) and Tabu Search (TS) algorithms. A customer selection based on a profitability analysis was carried out. The aforementioned algorithms were then applied, leading to a considerable reduction in the total logistic costs. This resulted in an improvement in the company's competitiveness and profit. [ABSTRACT FROM AUTHOR]

The global containerised trade heavily relies on liner shipping services, facilitating the worldwide movement of large cargo volumes along fixed routes and schedules. The profitability of shipping companies hinges on how efficiently they design their shipping network; a complex optimization problem known as the liner shipping network design problem (LSNDP). In recent years, approximate dynamic programming (ADP), also known as reinforcement learning, has emerged as a promising approach for large-scale optimisation. This paper introduces a novel Markov decision process for the LSNDP and investigates the potential of ADP. We show that ADP methods based on value iteration produce optimal solutions to small instances, but their scalability is hindered by high memory demands. An ADP method based on a deep neural network requires less memory and successfully obtains feasible solutions. The quality of solutions, however, declines for larger instances, possibly due to the discrete nature of high-dimensional state and action spaces. [ABSTRACT FROM AUTHOR]

In this study, we compare two methods for using neural networks to efficiently learn the price of derivatives. The first method, proposed by Funahashi (Quant Financ 21(4):575–592, 2021a), involves training the neural networks to learn the difference between the derivative price and its asymptotic expansion, rather than learning the derivative price directly. The target derivative price is then obtained by adding the approximate solution with the predicted value of neural networks. This method reduces the required amount of learning data, often by a factor of one hundred to one thousand, compared to the case where the derivative price is directly learned through neural networks. In the second method, established in this paper, the neural networks learn the difference between the derivative price written on the underlying asset price that follows the target complex stochastic process and the derivative price written on the underlying asset price that has a relatively simple stochastic process that has a closed-form solution for the target derivative prices. This method provides an alternative valuation method when no efficient approximate solution for the derivative value is observed and if one can arbitrarily determine the model parameters of the quasi-process that approximates the original process. We also propose a unified method to determine the model parameters of quasi-processes from underlying asset processes. These methods prove valuable in cases where general analytic solutions are absent, as seen in widely used financial models such as the stochastic volatility models. These cases involve time-consuming numerical calculations to generate learning data, highlighting the value of the two methods, which significantly compress calculation times. [ABSTRACT FROM AUTHOR]

This paper introduces AlphaVision, an innovative decision support model designed for stock price prediction by seamlessly integrating real-time news updates and Return on Investment (ROI) values, utilizing various machine learning and deep learning approaches. The research investigates the application of these techniques to enhance the effectiveness of stock trading and investment decisions by accurately anticipating stock prices and providing valuable insights to investors and businesses. The study begins by analyzing the complexities and challenges of stock market analysis, considering factors like political, macroeconomic, and legal issues that contribute to market volatility. To address these challenges, we proposed the methodology called AlphaVision, which incorporates various machine learning algorithms, including Decision Trees, Random Forest, Naïve Bayes, Boosting, K-Nearest Neighbors, and Support Vector Machine, alongside deep learning models such as Multi-layer Perceptron (MLP), Artificial Neural Networks, and Recurrent Neural Networks. The effectiveness of each model is evaluated based on their accuracy in predicting stock prices. Experimental results revealed that the MLP model achieved the highest accuracy of approximately 92%, outperforming other deep learning models. The Random Forest algorithm also demonstrated promising results with an accuracy of around 84.6%. These findings indicate the potential of machine learning and deep learning techniques in improving stock market analysis and prediction. The AlphaVision methodology presented in this research empowers investors and businesses with valuable tools to make informed investment decisions and navigate the complexities of the stock market. By accurately forecasting stock prices based on news updates and ROI values, the model contributes to better financial management and business sustainability. The integration of machine learning and deep learning approaches offers a promising solution for enhancing stock market analysis and prediction. Future research will focus on extracting more relevant financial features to further improve the model’s accuracy. By advancing decision support models for stock price prediction, researchers and practitioners can foster better investment strategies and foster economic growth. The proposed model holds potential to revolutionize stock trading and investment practices, enabling more informed and profitable decision-making in the financial sector. [ABSTRACT FROM AUTHOR]

Network reliability, named multistate stochastic cloud/edge-based network (MCEN) reliability afterwards, is defined as the probability that demands can be satisfied for an MCEN. It can be regarded as a performance indicator of the MCEN to measure the service capability. The concept of existing algorithms is to produce all of minimal system-state vectors for calculating MCEN reliability. However, such concept cannot response MCEN reliability in time when the MCEN scale becomes complicated in the Industry 4.0 environment. For providing MCEN reliability for decision making immediately, an architecture of a deep neural network (DNN) is developed to propose a prediction model for MCEN reliability such that MCEN capability with varied data can be learned promptly. To train the reliability prediction model, MCEN information is transformed to the suitable format, and the related information for DNN setting, including the determination of related functions, are defined with appropriate hyperparameters by using Bayesian Optimization. An illustrative case and a practical case of Amazon Web Service are provided to demonstrate the prediction model for MCEN reliability to show the availability and the efficiency. [ABSTRACT FROM AUTHOR]

Existing sales forecasting models are not comprehensive and flexible enough to consider dynamic changes and nonlinearities in sales time-series at the store and product levels. To capture different big data characteristics in sales forecasting data, such as seasonal and trend variations, this study develops a hybrid model combining adaptive trend estimated series (ATES) with a deep neural network model. ATES is first used to model seasonal effects and incorporate holiday, weekend, and marketing effects on sales. The deep neural network model is then proposed to model residuals by capturing complex high-level spatiotemporal features from the data. The proposed hybrid model is equipped with a feature-extraction component that automatically detects the patterns and trends in time-series, which makes the forecasting model robust against noise and time-series length. To validate the proposed hybrid model, a large volume of sales data is processed with a three-dimensional data model to effectively support business decisions at the product-specific store level. To demonstrate the effectiveness of the proposed model, a comparative analysis is performed with several state-of-the-art sales forecasting methods. Here, we show that the proposed hybrid model outperforms existing models for forecasting horizons ranging from one to 12 months. [ABSTRACT FROM AUTHOR]

Forecasting energy demand has been a critical process in various decision support systems regarding consumption planning, distribution strategies, and energy policies. Traditionally, forecasting energy consumption or demand methods included trend analyses, regression, and auto-regression. With advancements in machine learning methods, algorithms such as support vector machines, artificial neural networks, and random forests became prevalent. In recent times, with an unprecedented improvement in computing capabilities, deep learning algorithms are increasingly used to forecast energy consumption/demand. In this contribution, a relatively novel approach is employed to use long-term memory. Weather data was used to forecast the energy consumption from three datasets, with an additional piece of information in the deep learning architecture. This additional information carries the causal relationships between the weather indicators and energy consumption. This architecture with the causal information is termed as entangled long short term memory. The results show that the entangled long short term memory outperforms the state-of-the-art deep learning architecture (bidirectional long short term memory). The theoretical and practical implications of these results are discussed in terms of decision-making and energy management systems. [ABSTRACT FROM AUTHOR]

Hesitant attitudes have been a significant issue since the development of the first vaccines—the WHO sees them as one of the most critical global health threats. The increasing use of social media to spread questionable information about vaccination strongly impacts the population's decision to get vaccinated. Developing text classification methods that can identify hesitant messages on social media could be useful for health campaigns in their efforts to address negative influences from social media platforms and provide reliable information to support their strategies against hesitant-vaccination sentiments. This study aims to evaluate the performance of different machine learning models and deep learning methods in identifying vaccine-hesitant tweets that are being published during the COVID-19 pandemic. Our concluding remarks are that Long Short-Term Memory and Recurrent Neural Network models have outperformed traditional machine learning models on detecting vaccine-hesitant messages in social media, with an accuracy rate of 86% against 83%. [ABSTRACT FROM AUTHOR]

One of the most important composite indicators (CIs) to assess the development of countries or regions is the human development index (HDI) which is used by the United Nations (UN) to rank countries. HDI has three dimensions including healthy life, population education, and standard of living. A total of four different sub-indicators are defined for these three dimensions. The UN evaluates and ranks all countries using a simple arithmetic or geometric average of the sub-indicators and then categorizes the countries into four different groups based on their HDI scores. To measure the HDI, the benefit-of-the-doubt (BOD) model is used by researchers instead of the geometric mean. The conventional BOD model has some main drawbacks. The first is not accounting for data uncertainty, and the second is evaluating countries using different weights for the same sub-indicators. Furthermore, BOD model is not capable of predicting countries' future HDI scores. To overcome these deficiencies, this paper proposes a common weight fuzzy BOD (CWFBOD) model to measure the HDI scores. First, to take into account the uncertainty, data are considered fuzzy numbers, and a fuzzy BOD model (FBOD) is introduced. Then, to find a set of common weights for the three dimensions of HDI, the proposed FBOD model is transformed into a multiple-objective CWFBOD model. To convert and solve the multiple objective CWFBOD model to a single objective model, a fuzzy theory approach is used. In addition, of predicting the future HDI scores of countries, an artificial neural network (ANN) is designed and trained, where the original data on sub-indicators health, education, and income are considered as the features, and the HDI scores generated by CWBOD are assumed as the target of ANN. Finally, this study applies the fuzzy C-Means clustering technique to cluster all countries into four different clusters based on the HDI scores generated by FBOD and CWFBOD models. To illustrate the ability of the proposed methodology, the HDI scores of 190 countries during the period of 2015–2021 have been estimated and predicted. The results show that the proposed integrated methodology can be effectively used to estimate and predict the HDI scores as well as to cluster countries. [ABSTRACT FROM AUTHOR]

In this paper, an “intelligent” isolated intersection control system was developed. The developed “intelligent” system makes “real time” decisions as to whether to extend (and how much) current green time. The model developed is based on the combination of the dynamic programming and neural networks. Many tests show that the outcome (the extension of the green time) of the proposed neural network is nearly equal to the best solution. Practically negligible CPU times were achieved, and were thus absolutely acceptable for the “real time” application of the developed algorithm. [ABSTRACT FROM AUTHOR]

Conventional supervised learning in neural networks is carried out by performing unconstrained minimization of a suitably defined cost function. This approach has certain drawbacks, which can be overcome by incorporating additional knowledge in the training formalism. In this paper, two types of such additional knowledge are examined: Network specific knowledge (associated with the neural network irrespectively of the problem whose solution is sought) or problem specific knowledge (which helps to solve a specific learning task). A constrained optimization framework is introduced for incorporating these types of knowledge into the learning formalism. We present three examples of improvement in the learning behaviour of neural networks using additional knowledge in the context of our constrained optimization framework. The two network specific examples are designed to improve convergence and learning speed in the broad class of feedforward networks, while the third problem specific example is related to the efficient factorization of 2-D polynomials using suitably constructed sigma-pi networks. [ABSTRACT FROM AUTHOR]

Gelenbe et al. [1, 2] consider single server Jackson networks of queues which contain both positive and negative customers. A negative customer arriving to a nonempty queue causes the number of customers in that queue to decrease by one, and has no effect on an empty queue, whereas a positive customer arriving at a queue will always increase the queue length by one, Gelenbe et al. show that a geometric product form equilibrium distribution prevails for this network. Applications for these types of networks can be found in systems incorporating resource allocations and in the modelling of decision making algorithms, neural networks and communications protocols. In this paper we extend the results of [1, 2] by allowing customer arrivals to the network, or the transfer between queues of a single positive customer in the network to trigger the creation of a batch of negative customers at the destination queue. This causes the length of the queue to decrease by the size of the created batch or the size of the queue, whichever is the smallest. The probability of creating a batch of negative customers of a particular size due to the transfer of a positive customer can depend on both the source and destination queue. We give a criterion for the validity of a geometric product form equilibrium distribution for these extended networks. When such a distribution holds it satisfies partial balance equations which are enforced by the boundaries of the state space. Furthermore it will be shown that these partial balance equations relate to traffic equations for the throughputs of the individual queues. [ABSTRACT FROM AUTHOR]

Since the establishment of the Shanghai Stock Exchange (SHSE) in 1990 and the Shenzhen Stock Exchange (SZSE) in 1991, China's stock markets have expanded rapidly. Although this rapid growth has attracted considerable academic interest, few studies have examined the ability of conventional financial models to predict the share price movements of Chinese stock. This gap in the literature is significant, given the volatility of the Chinese stock markets and the added risk that arises from the Chinese legal and regulatory environment. In this paper we address this research gap by examining the predictive ability of several well-established forecasting models, including dynamic versions of a single-factor CAPM-based model and Fama and French's three-factor model. In addition, we compare the forecasting ability of each of these models with that of an artificial neural network (ANN) model that contains the same predictor variables but relaxes the assumption of model linearity. Surprisingly, we find no statistical differences in the forecasting accuracy of the CAPM and three-factor model, a result that may reflect the emerging nature of the Chinese stock markets. We also find that each ANN model outperforms the corresponding linear model, indicating that neural networks may be a useful tool for stock price prediction in emerging markets. [ABSTRACT FROM AUTHOR]

The operations research is probably one of the most successful field of applied mathematics used in economics, physics, chemistry, almost everywhere where one has to analyze huge amounts of data. Lately, these techniques of operations research were introduced in biology, especially in the protein analysis area to support biologists. The fast growth of protein data makes operations research an important issue in bioinformatics, a science which lays on the border between computer science and biology. This paper gives a short overview of the operations research techniques currently used to support structural and functional analysis of proteins. [ABSTRACT FROM AUTHOR]

The augmented-neural-network (AugNN) approach has been applied lately to some NP-Hard combinatorial problems, such as task scheduling, open-shop scheduling and resource-constraint project scheduling. In this approach the problem of search in the solution-space is transformed to a search in a weight-matrix space, much like in a neural-network approach. Some weight adjustment strategies are then used to converge to a good set of weights for a locally optimal solution. While empirical results have demonstrated the effectiveness of the AugNN approach vis-à-vis a few other metaheuristics, little theoretical insights exist which justify this approach and explain the effectiveness thereof. This paper provides some theoretical insights and justification for the AugNN approach through some basic theorems and also describes the algorithm and the formulation with the help of examples. [ABSTRACT FROM AUTHOR]

While in location planning it is often assumed that deliveries are made on a direct-trip basis, in fact deliveries, e.g., to the different supermarkets belonging to a specific chain or to retail outlets of any kind, usually are performed as round-trips. Therefore, it is often necessary to combine the two issues of locating a depot and of planning tours in one problem formulation. In this paper, a neural network approach based on a self-organizing map is proposed for solving such single-depot location-routing problems in the plane. The results derived by this approach are compared with those which can be found by different well-known heuristics, and it is shown that the self-organising map approach competes well with these concepts. Moreover, some modifications which rely on ideas from Tabu Search can be shown to be especially useful for increasing the number of feasible solutions found by the self-organising map approach. Finally, the implementation of the Weiszfeld procedure for a final improvement of the optimal depot location proves to be a useful device. [ABSTRACT FROM AUTHOR]

Recognition of preconflict situations has a powerful potential for early warning of violent political conflicts. This paper focuses on the design and application of artificial neural networks as classifiers of preconflict situations. Achieving a desired level of performance of the neural network relies on the appropriate construction of recognition space (selection of indicators) and the choice of network architecture. A fast and effective method for the design of reliable neural recognition systems is described. It is based on genetic algorithm techniques and optimizes both the configuration of input space and the network parameters. The implementation of the methodology provides for increased performance of the classifier in terms of accuracy, generalization capacity, computational and data requirements. [ABSTRACT FROM AUTHOR]

COVID-19 is a highly prevalent disease that has led to numerous predicaments for healthcare systems worldwide. Owing to the significant influx of patients and limited resources of health services, there have been several limitations associated with patients' hospitalization. These limitations can cause an increment in the COVID-19-related mortality due to the lack of appropriate medical services. They can also elevate the risk of infection in the rest of the population. The present study aims to investigate a two-phase approach to designing a supply chain network for hospitalizing patients in the existing and temporary hospitals, efficiently distributing medications and medical items needed by patients, and managing the waste created in hospitals. Since the number of future patients is uncertain, in the first phase, trained Artificial Neural Networks with historical data forecast the number of patients in future periods and generate scenarios. Through the use of the K-Means method, these scenarios are reduced. In the second phase, a multi-objective, multi-period, data-driven two-stage stochastic programming is developed using the acquired scenarios in the previous phase concerning the uncertainty and disruption in facilities. The objectives of the proposed model include maximizing the minimum allocation-to-demand ratio, minimizing the total risk of disease spread, and minimizing the total transportation time. Furthermore, a real case study is investigated in Tehran, the capital of Iran. The results showed that the areas with the highest population density and no facilities near them have been selected for the location of temporary facilities. Among temporary facilities, temporary hospitals can allocate up to 2.6% of the total demand, which puts pressure on the existing hospitals to be removed. Furthermore, the results indicated that the allocation-to-demand ratio can remain at an ideal level when disruptions occur by considering temporary facilities. Our analyses focus on: (1) Examining demand forecasting error and generated scenarios in the first phase, (2) exploring the impact of demand parameters on the allocation-to-demand ratio, total time and total risk, (3) investigating the strategy of utilizing temporary hospitals to address sudden changes in demand, (4) evaluating the effect of disruption to facilities on the supply chain network. [ABSTRACT FROM AUTHOR]

This paper deals with the demand for money, including narrow money (M1) and broad money (A2) in China. We use the cointegration and error-correction model to formulate the function of money demand and merge the short-run and long-run equations to give forecasts over different horizons. In particular, we combine very simple artificial neural networks (ANNs) with the cointegration and error-correction model to give a nonlinear model. These models are quarterly models, sampled from the first quarter of 1980 to the fourth quater of 1994, and the multi-step forecasts are from the first quarter of 1990 to the fourth quarter of 1994. Both the fitted values and predictive values for M1 and A2 are satisfactory. Finally, we give forecasts for M2 from the first quarter of 1995 to the second quarter of 1996. [ABSTRACT FROM AUTHOR]

In the orienteering problem, we are given a transportation network in which a start point and an end point are specified. Other points have associated scores. Given a fixed amount of time, the goal is to determine a path from start to end through a subset of locations in order to maximize the total path score. This problem has received a considerable amount of attention in the last ten years. The traveling salesman problem is a variant of the orienteering problem. This paper applies a modified, continuous Hopfield neural network to attack this NP-hard optimization problem. In it, we design an effective energy function and learning algorithm. Unlike some applications of neural networks to optimization problems, this approach is shown to perform quite well. [ABSTRACT FROM AUTHOR]

A neural network model for solving an assortment problem found in the iron and steel industry is discussed in this paper. The problem arises in the yard where steel plate is cut into rectangular pieces. The neural network model can be categorized as a Hopfield model, but the model is expanded to handle inequality constraints. The idea of a penalty function is used. A large penalty is applied to the network if a constraint is not satisfied. The weights are updated based on the penalty values. A special term is added to the energy function of the network to guarantee the convergence of the neural network which has this feature. The performance of the neural network was evaluated by comparison with an existing expert system. The results showed that the neural network has the potential to identify in a short time near-optimal solutions to the assortment problem. The neural network is used as the core of a system for dealing with the assortment problem. In building the neural networks system for practical use, there were many implementation issues. Some of them are presented here, and the fundamental ideas are explained. The performance of the neural network system is compared to that of the expert system and evaluated from the practical viewpoint. The results show that the neural network system is useful in handling the assortment problem. [ABSTRACT FROM AUTHOR]

We compare the performance of various advanced forecasting techniques, namely artificial neural networks, k-nearest neighbors, logistic regression, Naïve Bayes, random forest classifier, support vector machine, and extreme gradient boosting classifier to predict stock price movements based on past prices. We apply these methods with the high frequency data of 27 blue-chip stocks traded in the Istanbul Stock Exchange. Our findings reveal that among the selected methodologies, random forest and support vector machine are able to capture both future price directions and percentage changes at a satisfactory level. Moreover, consistent ranking of the methodologies across different time frequencies and train/test set partitions prove the robustness of our empirical findings. [ABSTRACT FROM AUTHOR]

Competition between times series often arises in sales prediction, when similar products are on sale on a marketplace. This article provides a model of the presence of cannibalization between times series. This model creates a "competitiveness" function that depends on external features such as price and margin. It also provides a theoretical guaranty on the error of the model under some reasonable conditions, and implement this model using a neural network to compute this competitiveness function. This implementation outperforms other traditional time series methods and classical neural networks for market share prediction on a real-world data set. Moreover, it allows controlling underprediction, which plagues traditional forecasts models. [ABSTRACT FROM AUTHOR]

Quality inspection is essential in preventing defective products from entering the market. Due to the typically low percentage of defective products, it is generally challenging to detect them using algorithms that aim for the overall classification accuracy. To help solve this problem, we propose an ensemble learning classification model, where we employ adaptive boosting (AdaBoost) to cascade multiple backpropagation (BP) neural networks. Furthermore, cost-sensitive (CS) learning is introduced to adjust the loss function of the basic classifier of the BP neural network. For clarity, this model is called a CS-AdaBoost-BP model. To empirically verify its effectiveness, we use data from home appliance production lines from Bosch. We carry out tenfold cross-validation to evaluate and compare the performance between the CS-AdaBoost-BP model and three existing models: BP neural network, BP neural network based on sampling, and AdaBoost-BP. The results show that our proposed model not only performs better than the other models but also significantly improves the ability to identify defective products. Furthermore, based on the mean value of the Youden index, our proposed model has the highest stability. [ABSTRACT FROM AUTHOR]

Knowledge management is widely considered as a strategic tool to increase firm performance by enabling the reuse of organizational knowledge. Although many have studied knowledge management in a variety of business settings, the concept of tacit knowledge, especially the individual one, has not been explored in due detail. The objective of this study is to identify and prioritize individual tacit knowledge criteria and to explain their effects on firm performance. In the proposed methodology, first, the most prevalent individual tacit knowledge variables are identified by means of knowledge elicitation and feature selection methods. Then, the extracted variables were prioritized using machine learning methods and fuzzy Analytic Hierarchy Process (AHP). Support vector machine (SVM), logistic regression, and artificial neural networks are used as the first approach, followed by fuzzy AHP as the second approach. Based on the comparative analysis results, SVM (as the best-performed machine-learning technique) and fuzzy AHP methods were identified for the subsequent analysis. The results showed that both SVM and fuzzy AHP determined time efficiency of employees, communication between employees and supervisors, and innovative capability of employees as the most important tacit knowledge criteria. These findings are mostly supported by the extant literature, and collectively shows the synergistic nature of the utilized analytics approaches in determining individual tacit knowledge criteria. [ABSTRACT FROM AUTHOR]

Metaheuristics are the most exciting development in approximate optimization techniques of the last two decades. They have had widespread successes in attacking a variety of difficult combinatorial optimization problems that arise in many practical areas. This bibliography provides a classification of a comprehensive list of 1380 references on the theory and application of metaheuristics. Metaheuristics include but are not limited to constraint logic programming; greedy random adaptive search procedures; natural evolutionary computation; neural networks; non-monotonic search strategies; space-search methods; simulated annealing; tabu search; threshold algorithms and their hybrids. References are presented in alphabetical order under a number of subheadings. [ABSTRACT FROM AUTHOR]

In this study, the predictability of the most liquid twelve cryptocurrencies are analyzed at the daily and minute level frequencies using the machine learning classification algorithms including the support vector machines, logistic regression, artificial neural networks, and random forests with the past price information and technical indicators as model features. The average classification accuracy of four algorithms are consistently all above the 50% threshold for all cryptocurrencies and for all the timescales showing that there exists predictability of trends in prices to a certain degree in the cryptocurrency markets. Machine learning classification algorithms reach about 55–65% predictive accuracy on average at the daily or minute level frequencies, while the support vector machines demonstrate the best and consistent results in terms of predictive accuracy compared to the logistic regression, artificial neural networks and random forest classification algorithms. [ABSTRACT FROM AUTHOR]

The increasing number of new higher education institutions (HEIs) has resulted in a fierce competition for attracting and retaining the best students. In line with these purposes, this study is aimed at devising a student satisfaction index (SSI) model for the HEIs. The SSI model is developed to measure the satisfaction of students in terms of different aspects such as image of the university, expectations, perceived quality, perceived value, and loyalty. The SSI model was developed using the Bayesian neural networks-based Universal Structure Modeling method. The results provide strategically valuable information for HEIs decision makers with regard to influential factors of student satisfaction and loyalty. [ABSTRACT FROM AUTHOR]

Diversification is one of the most effective approaches to defend multitier systems against attacks, failure, and accidents. However, designing such a system with effective diversification is a challenging task because of stochastic user and attacker behaviors, combinatorial-explosive solution space, and multiple conflicting design objectives. In this study, we present a systematic framework for exploring the solution space, and consequently help the designer select a satisfactory system solution. A simulation model is employed to evaluate design solutions, and an artificial neural network is trained to approximate the behavior of the system based on simulation output. Guided by a trained neural network, a multi-objective evolutionary algorithm (MOEA) is proposed to search the solution space and identify potentially good solutions. Our MOEA incorporates the concept of Herbert Simon's satisficing. It uses the decision maker's aspiration levels for system performance metrics as its search direction to identity potentially good solutions. Such solutions are then evaluated via simulation. The newly-obtained simulation results are used to refine the neural network. The exploration process stops when the result converges or a satisfactory solution is found. We demonstrate and validate our framework using a design case of a three-tier web system. [ABSTRACT FROM AUTHOR]

This study compares the predictive performance of three neural network methods, namely the learning vector quantization, the radial basis function, and the feedforward network that uses the conjugate gradient optimization algorithm, with the performance of the logistic regression and the backpropagation algorithm. All these methods are applied to a dataset of 139 matched-pairs of bankrupt and non-bankrupt US firms for the period 1983–1994. The results of this study Indicate that the contemporary neural network methods applied in the present study provide superior results to those obtained from the logistic regression method and the backpropagation algorithm. [ABSTRACT FROM AUTHOR]

The prediction of long-run operating performance of new ventures, known as Initial Public Offerings (IPOs), represents a challenging decision problem. Factors adding to the complexity of the problem include asymmetrically informed agents, incentive problems, and inability to specify functional relationships between variables. Research literature identifying determinants of long-run performance of new issues is limited. This study uses a data driven, nonparametric, neural network based approach to predict the long-run operating performance of new ventures. The classification accuracy of the neural network model is compared with that of a logit model. Methodological issues such as sample design and estimation of optimal cutoff probabilities for classification are addressed. The results suggest that the neural networks generally outperform logit models. [ABSTRACT FROM AUTHOR]

We investigate the possibility of applying artificial intelligence to solve an audit decision problem faced by the public sector (namely, the tax auditor of the Internal Revenue Services) when targeting firms for further investigation. We propose that the neural network will overcome problems faced by a direct knowledge acquisition method in building an expert system to preserve the expertise of senior auditors of the IRS in Taiwan. An explanation of the neural network theory is provided with regard to multi- and single-layered neural networks. Statistics reveal that the neural network performs favorably, and that three-layer networks perform better than two-layer neural networks. The results strongly suggest that neural networks can be used to identify firms requiring further auditing investigation, and also suggest future implications for intelligent auditing machines. [ABSTRACT FROM AUTHOR]

We survey results concerning a new stochastic network we have developed [1–7], which was initially motivated by neural network modelling [1], or - as we called it - by queueing networks with positive and negative customers [2, 3]. Indeed, it is well known that signals in neural networks are formed by impulses or action potentials, traveling much like customers in a queueing network. We call this model a G-network because it serves as a unifying basis for diverse areas of stochastic modelling in queueing networks, computer networks, computer system performance and neural networks. In its simplest version, ‘negative’ and ‘positive’ signals or customers circulate among a finite set of units, modelling inhibitory and excitatory signals of a neural network, or ‘negative and positive customers’ of a queueing network. Signals can arrive either from other units or from the outside world. Positive signals are accumulated at the input of each unit, and constitute its signal potential. The state of each unit or neuron is its signal potential (which is equivalent to the queue length), while the network state is the vector of signal potentials at each neuron. If its potential is positive, a unit or neuron fires, and sends out signals to the other neurons or to the outside world. As it does so, its signal potential is depleted. In the Markovian case, this model has product form, i.e. the steady-state probability distribution of its potential vector is the product of the marginal probabilities of the potential at each neuron. The signal flow equations of the network, which describe the rate at which positive or negative signals arrive to each neuron, are non-linear. We discuss the relationship between this model and the usual connectionist (formal) model of neural networks, and present applications to combinatorial optimization and to image texture processing. Extensions of the model to the case of ‘multiple signal classes’, and to ‘networks with triggered customer motion’ are presented. We also examine the general stability conditions which guarantee that the network has a well-defined steady-state behaviour. [ABSTRACT FROM AUTHOR]