Text-based crude oil price forecasting: A deep learning approach

This study proposes a new, novel crude oil price forecasting method based on online media text mining, with the aim of capturing the more immediate market antecedents of price fluctuations. Specifically, this is an early attempt to apply deep learning techniques to crude oil forecasting, and to extract hidden patterns within online news media using a convolutional neural network (CNN). While the news-text sentiment features and the features extracted by the CNN model reveal significant relationships with the price change, they need to be grouped according to their topics in the price forecasting in order to obtain a greater forecasting accuracy. This study further proposes a feature grouping method based on the Latent Dirichlet Allocation (LDA) topic model for distinguishing effects from various online news topics. Optimized input variable combination is constructed using lag order selection and feature selection methods. Our empirical results suggest that the proposed topic-sentiment synthesis forecasting models perform better than the older benchmark models. In addition, text features and financial features are shown to be complementary in producing more accurate crude oil price forecasts.     

A multiobjective optimization model for project selection with probabilistic considerations

When faced with limited resources, project managers must determine which projects to fund at what levels from a pool of potential ones. This problem of project selection is inherently multiobjective since various factors, such as the available budget, the chance of success, and the efficient allocation of the project team, must be considered simultaneously. The uncertainty of the data at the time decisions are made further complicates project selection. In this paper, a multiobjective, integer-constrained optimization model with competing objectives for project selection is formulated using probability distributions to describe costs. The objectives correspond to important project criteria, such as: rank (value), managerial labor needed, and average cost. The subjective rank is determined via the Analytic Hierarchy Process. The model is applied to a data set from a US government agency that involves 84 separate projects. The results indicate improved budgetary efficiency compared to the actual project selection, thus supporting use of the model for public sector project selection. The model is unique since it integrates multiobjective optimization, Monte Carlo simulation, and the Analytic Hierarchy Process.     

Improving forecast stability using deep learning

In this paper, we define forecast (in)stability in terms of the variability in forecasts for a specific time period caused by updating the forecast for this time period when new observations become available, i.e., as time passes. We propose an extension to the state-of-the-art N-BEATS deep learning architecture for the univariate time series point forecasting problem. The extension allows us to optimize forecasts from both a traditional forecast accuracy perspective as well as a forecast stability perspective. We show that the proposed extension results in forecasts that are more stable without leading to a deterioration in forecast accuracy for the M3 and M4 data sets. Moreover, our experimental study shows that it is possible to improve both forecast accuracy and stability compared to the original N-BEATS architecture, indicating that including a forecast instability component in the loss function can be used as regularization mechanism.     

A cognitive hierarchy model of learning in networks

This paper proposes a method for estimating a hierarchical model of bounded rationality in games of learning in networks. A cognitive hierarchy comprises a set of cognitive types whose behavior ranges from random to substantively rational. Specifically, each cognitive type in the model corresponds to the number of periods in which economic agents process new information. Using experimental data, we estimate type distributions in a variety of task environments and show how estimated distributions depend on the structural properties of the environments. The estimation results identify significant levels of behavioral heterogeneity in the experimental data and overall confirm comparative static conjectures on type distributions across task environments. Surprisingly, the model replicates the aggregate patterns of the behavior in the data quite well. Finally, we found that the dominant type in the data is closely related to Bayes-rational behavior.     

一种基于对象工作流网的学习过程模型

为了对E-learning的学习过程建模,采用双层建模技术,下层是语言描述层,以WfMC提出的XPDL为基础,结合学习领域的具体领域特征,对学习过程进行形式化描述,上层是流程逻辑层,采用对象Petri网实现,可以对下层模型进行数学上的分析、验证,保证所建模型的正确性、完整性,同时又可解决普通Petri网在规模过大时容易出现的状态爆炸问题。     

An optimization model for planning community health services.

This article reports results of a project to develop methods of planning health care delivery for a community with emphasis on ambulatory services in a health maintenance organization setting. Some of the special difficulties of the problem are discussed and a linear optimization model is presented that addresses the problem of planning the ambulatory service mix for a specified population. The model accounts for population characteristics, financial data, and system dynamics (including referral patterns). An application is shown for the case of a “model cities” population in Buffalo, New York, and some implications for further research are presented.     

Consumption optimization for recursive utility in a jump-diffusion model

In this paper, we consider a market model with prices and consumption following a jump-diffusion dynamics. In this setting, we first characterize the optimal consumption plan for an investor with recursive stochastic differential utility on the basis of his/her own beliefs, then we solve the inverse problem to find what beliefs make a given consumption plan optimal. The problem is viewed in general for a class of homogeneous recursive utility, and later we choose a logarithmic model for the utility aggregator as an explicitly computable example. When beliefs, represented via Girsanov’s theorem, get incorporated into the model, the change of measure gives rise, up to a transformation, to a backward stochastic differential equation whose generator exhibits a quadratic behavior in the Brownian component and a locally Lipschitz one in the jump component, which is solvable on the basis of some recent results.     

An optimization model for volunteer assignments in humanitarian organizations

One of the challenges facing humanitarian organizations is that there exist limited decision technologies that are tailored specifically to their needs. While employee workforce management models have been the topic of extensive research over the past decades, very little work has yet concentrated on the problem of managing volunteers for humanitarian organizations. This paper develops a multi-criteria optimization model to assist in the assignment of volunteers to tasks, based upon a series of principles from the field of volunteer management. In particular, it offers a new volunteer management approach for incorporating the decision maker's preferences and knowledge into the volunteer assignment process, thus allowing him or her to closely examine the tradeoffs between potentially conflicting objectives. Test results illustrate the model's ability to capture these tradeoffs and represent the imprecision inherent in the work of humanitarian organizations, and thus demonstrate its ability to support efficient and effective volunteer management.     

Production planning and inventories optimization: A backward approach in the convex storage cost case

We study the deterministic optimization problem of a profit-maximizing firm which plans its sales/production schedule. The firm controls both its production and sales rates and knows the revenue associated to a given level of sales, as well as its production and storage costs. The revenue and the production cost are assumed to be respectively concave and convex. In Chazal et al. [Chazal, M., Jouini, E., Tahraoui, R., 2003. Production planning and inventories optimization with a general storage cost function. Nonlinear Analysis 54, 1365–1395], we provide an existence result and derive some necessary conditions of optimality. Here, we further assume that the storage cost is convex. This allows us to relate the optimal planning problem to the study of a backward integro-differential equation, from which we obtain an explicit construction of the optimal plan.     

Comparing supervised learning algorithms and artificial neural networks for conflict prediction: performance and applicability of deep learning in the field

Quality & Quantity - Machine learning algorithms and artificial neural networks promise a new and powerful approach for making better and more transferable predictions in global conflict...     

The modified Huang’s cost model for process optimization

In 2001, Huang presented the problem of determining the optimum process mean and standard deviation based on considering the trade-off relationship between the process adjustment cost and the quality loss of product. They considered the normal quality characteristic and adopted the quadratic quality loss function for measuring the product quality. In this paper, we further propose the problem of process optimization and reconsider the modified Huang’s model under the specified process capability index value for determining the optimum process parameters. The symmetric quadratic, asymmetric quadratic, and asymmetric linear quality loss functions will be adopted for evaluating the product quality. Finally, the numerical example and the sensitivity analysis of parameters will be provided for illustration.     

一种嵌入式系统存储管理方案

实时性、可靠性的要求,使得许多嵌入式应用程序需要使用自己的存储管理程序,文章探讨了嵌入式系统对存储管理系统的要求、存在的问题以及可能的解决方案,并给出一种存储管理的具体实现方案。     

Stochastic optimization model for distribution and evacuation planning (A case study of Tehran earthquake)

In this study, a stochastic multi-objective mixed-integer mathematical programming is proposed for logistic distribution and evacuation planning during an earthquake. Decisions about the pre- and post-phases of the disaster are considered seamless. The decisions of the pre-disaster phase relate to the location of permanent relief distribution centers and the number of the commodities to be stored. The decisions of the second phase are to determine the optimal location for the establishment of temporary care centers to increase the speed of treating the injured people and the distribution of the commodities at the affected areas. Humanitarian and cost issues are considered in the proposed models through three objective functions. Several sets of constraints are also considered in the proposed model to make it flexible to handle real issues. Demands for food, blood, water, blanket, and tent are assumed to be probabilistic which are related to several complicated factors and modeled using a complicated network in this study. A simulation is setup to generate the probabilistic distribution of demands through several scenarios. The stochastic demands are assumed as inputs for the proposed stochastic multi-objective mixed integer mathematical programming model.The model is transformed to its deterministic equivalent using chance constraint programming approach. The equivalent deterministic model is solved using an efficient epsilon-constraint approach and an evolutionary algorithm, called non-dominated sorting genetic algorithm (NSGA-II). First several illustrative numerical examples are solved using both solution procedures. The performance of solution procedures is compared and the most efficient solution procedure, i.e., NSGA-II, is used to handle the case study of Tehran earthquake. The results are promising and show that the proposed model and the solution approach can handle the real case study in an efficient way.     

A resilience-based model for performance evaluation of information systems: the case of a gas company

Information systems (IS) are strongly influenced by changes in new technology and should react swiftly in response to external conditions. Resilience engineering is a new method that can enable these systems to absorb changes. In this study, a new framework is presented for performance evaluation of IS that includes DeLone and McLean’s factors of success in addition to resilience. Hence, this study is an attempt to evaluate the impact of resilience on IS by the proposed model in Iranian Gas Engineering and Development Company via the data obtained from questionnaires and Fuzzy Data Envelopment Analysis (FDEA) approach. First, FDEA model with α-cut = 0.05 was identified as the most suitable model to this application by performing all Banker, Charnes and Cooper and Charnes, Cooper and Rhodes models of and FDEA and selecting the appropriate model based on maximum mean efficiency. Then, the factors were ranked based on the results of sensitivity analysis, which showed resilience had a significantly higher impact on the proposed model relative to other factors. The results of this study were then verified by conducting the related ANOVA test. This is the first study that examines the impact of resilience on IS by statistical and mathematical approaches.     

A New Keynesian model with staggered price and wage setting under learning

This paper provides a study of the implications for economic dynamics when the central bank sets its nominal interest rate target in response to variations in wage inflation. I provide results on the existence, uniqueness, and stability under learning of rational expectations equilibrium for alternative specifications of the manner in which monetary policy responds to economic shocks when nominal rigidities are present. Monopolistically competitive producers set prices via staggered price contracts, and households set nominal wages in the same fashion. In this setting, the conditions for determinacy and learnability of rational expectations equilibrium differ from a model where only prices are sticky. I find that when the central bank responds to wage and price inflation and to the output gap, a Taylor principle for wage and price inflation arises that is related to stability under learning dynamics. In other words, a moderate reaction of the interest rate to wage inflation helps to avoid instability under learning and indeterminacy.     

The empirical relevance of the competitive storage model

The empirical relevance of models of competitive storage arbitrage in explaining commodity price behavior has been seriously challenged in a series of pathbreaking papers by [Deaton and Laroque, 1992], [Deaton and Laroque, 1995] and [Deaton and Laroque, 1996]. Here we address their major criticism, that the model is in general unable to explain the degree of serial correlation observed in the prices of twelve major commodities. First, we present a simple numerical version of their model which, contrary to Deaton and Laroque (1992), can generate the high levels of serial correlation observed in commodity prices, if it is parameterized to generate realistic levels of price variation. Then, after estimating the [Deaton and Laroque, 1995] and [Deaton and Laroque, 1996] model using their data set, model specification and econometric approach, we show that the use of a much finer grid to approximate the equilibrium price function yields quite different estimates for most commodities. Results are obtained for coffee, copper, jute, maize, palm oil, sugar and tin that support the specifications of the storage model with positive constant marginal storage cost and no deterioration as in Gustafson (1958a). Consumption demand has a low response to price and, except for sugar, stockouts are infrequent. The observed magnitudes of serial correlation of price match those implied by the estimated model.     

Improved hybrid resampling and ensemble model for imbalance learning and credit evaluation

A clustering-based undersampling (CUS) and distance-based near-miss method are widely used in current imbalanced learning algorithms, but this method has certain drawbacks. In particular, the CUS does not consider the influence of the distance factor on the majority of instances, and the near-miss method omits the inter-class(es) within the majority of samples. To overcome these drawbacks, this study proposes an undersampling method combining distance measurement and majority class clustering. Resampling methods are used to develop an ensemble-based imbalanced-learning algorithm called the clustering and distance-based imbalance learning model (CDEILM). This algorithm combines distance-based undersampling, feature selection, and ensemble learning. In addition, a cluster size-based resampling (CSBR) method is proposed for preserving the original distribution of the majority class, and a hybrid imbalanced learning framework is constructed by fusing various types of resampling methods. The combination of CDEILM and CSBR can be considered as a specific case of this hybrid framework. The experimental results show that the CDEILM and CSBR methods can achieve better performance than the benchmark methods, and that the hybrid model provides the best results under most circumstances. Therefore, the proposed model can be used as an alternative imbalanced learning method under specific circumstances, e.g., for providing a solution to credit evaluation problems in financial applications.