Intelligent Systems in Accounting, Finance and Management最新文献

Location prediction is essential to many commercial applications and enables appealing experience for business and governments. Many research work show that human mobility is highly predictable. However, existing work on location prediction reported limited improvements in using generalized spatio-temporal features and unsatisfactory prediction accuracy for complex human mobility. To address these challenges, in this paper we propose a Mobility Intention and Auto-Completion (MIAC) model. We extract those mobility patterns that generalize common spatio-temporal features of all users, and use the mobility intentions as the hidden states from mobility dataset. A new predicting algorithm based on auto-completion is then proposed. The experimental results on real-world datasets demonstrate that the proposed MIAC model can properly capture the regularity of a user's mobility by simultaneously considering the spatial and temporal features. The comparison results also indicate that MIAC model significantly outperforms state-of-the-art location prediction methods, and also can predicts long range locations.

The objective of this paper is twofold. First, it develops a prediction system to help the credit card issuer model the credit card delinquency risk. Second, it seeks to explore the potential of deep learning (also called a deep neural network), an emerging artificial intelligence technology, in the credit risk domain. With real-life credit card data linked to 711,397 credit card holders from a large bank in Brazil, this study develops a deep neural network to evaluate the risk of credit card delinquency based on the client's personal characteristics and the spending behaviours. Compared with machine-learning algorithms of logistic regression, naive Bayes, traditional artificial neural networks, and decision trees, deep neural networks have a better overall predictive performance with the highest F scores and area under the receiver operating characteristic curve. The successful application of deep learning implies that artificial intelligence has great potential to support and automate credit risk assessment for financial institutions and credit bureaus.

We introduce a computational agent-based model of innovation diffusion that allows us to analyse the influence of information and communication technology (ICT) development on decision-making. Model dynamics are based on local emulation between pairs of individuals that generate an evolving social network on which an innovation is virally spread (by word of mouth). Results suggest that ICT development affects the data usefulness for decision-making by changing the topology of the social network (the means whereby the innovation is propagated). Paradoxically, a higher level of ICT development (providing a larger volume of data) narrows the differences between better and worse launch strategies, thus reducing data-driven decision-making usefulness, which then shows diminishing returns on the ICT level.

The aim of this paper is to propose a comprehensive framework for simultaneously measuring the performance of sustainable service and manufacturing supply chain management. Application of the proposed approach also results in reduced uncertainty of the performance measurement process caused by qualitative criteria evaluation. The proposed approach consists of two main steps. First, the fuzzy decision-making trial and evaluation laboratory (DEMATEL) method has been used to determine important criteria by avoiding low influences; and then a Mamdani fuzzy inference system model has been adopted and applied for performance evaluation of sustainable supply chain management (SSCM). This model is employed in order to cope with the vagueness that exists in the SSCM performance investigation due to the vagueness intrinsic in the evaluation of criteria. In the proposed model, human reasoning has been modelled with fuzzy inference rules and has been set in the system, which is an advantage compared with those models in which fuzzy set theory and multicriteria decision-making models are integrated. The proposed approach has been implemented in the pipe and fitting industry in order to highlight its application in real life. Sensitivity analysis has been carried out to determine the influence of service and manufacturing criteria on SSCM performance. The findings reveal that sustainable manufacturing criteria compared with sustainable service criteria have more effect on the performance of SSCM.

Directional Change (DC) is a technique to summarize price movements in a financial market. According to the DC concept, data is sampled only when the magnitude of price change is significant according to the investor. In this paper, we develop a contrarian trading strategy named TSFDC. TSFDC is based on a forecasting model which aims to predict the change of the direction of market's trend under the DC context. We examine the profitability, risk and risk-adjusted return of TSFDC in the FX market using eight currency pairs. The results suggest that TSFDC outperforms the buy and hold approach and another DC-based trading strategy.

There has been much interest in copulas, which are known to provide a flexible tool for analyzing the dependence structure among random variables. Dependence relations must be dynamic rather than static in nature. However, copulas are useful mainly for static matters. Thus we introduce evolving multivariate copulas, which transform through time autonomously governed by the multivariate heat equation. Our aims are to prove their existences and solutions to analyze their transitions. Moreover, we construct discrete type to apply empirical data analysis and investigate their properties, and prove that they converge to their original continuous type.

An interesting research problem in our age of Big Data is that of determining provenance. Granular evaluation of provenance of physical goods (e.g., tracking ingredients of a pharmaceutical or demonstrating authenticity of luxury goods) has often not been possible with today's items that are produced and transported in complex, interorganizational, often internationally spanning supply chains. Recent adoptions of the Internet of Things and blockchain technologies give promise at better supply-chain provenance. We are particularly interested in the blockchain, as many favored use cases of blockchain are for provenance tracking. We are also interested in applying ontologies, as there has been some work done on knowledge provenance, traceability, and food provenance using ontologies. In this paper, we make a case for why ontologies can contribute to blockchain design. To support this case, we analyze a traceability ontology and translate some of its representations to smart contracts that execute a provenance trace and enforce traceability constraints on the Ethereum blockchain platform.

The context to be addressed is the digitalization of industry and industrial processes. Digitalization brings enhanced customer relationships and value-chain integration, which are effective instruments to meet increasing competition and slimmer margins for productivity and profitability. Digitalization also brings more pronounced requirements for effective planning, problem solving and decision making in an increasingly complex and fast-changing environment. Decision analytics will meet the challenges from the growing global competition that major industrial corporations face and will help solve the problems of big data/fast data that digitalization is generating as a by-product. A mantra is appearing in business magazines – that powerful, intelligent systems will be effective tools for the digitalization of industrial processes – but much less attention appears to be paid to the fact that users need advanced knowledge and skills to benefit from the intelligent systems. First, an effective transfer of knowledge from developers, experts and researchers to users (including management) will be needed; second, the daily use and operations of the systems need to be supported, as automated, intelligent industrial systems are complex to operate. We look at this transfer as knowledge mobilization and will work out how the mobilization can be supported with coaching; this coaching needs to be digital, as human coaches are both scarce and too expensive to employ in large numbers.

This paper creates a market ecosystem, via an agent-based model, that combines the dynamic features of the Red Queen effect with well-accepted business world performance indicators. Essentially, firms are tasked with remaining ‘alive’ by adapting to their environment through implementing a competitive response of innovating or imitating. An analysis of the firms’ behaviours delivers a deep understanding of the drivers of innovative behaviour within the economy. The key findings of the paper are (1) that concentrated markets are not entirely detrimental to innovative behaviour, with the blend of firm type being a more important consideration, and (2) that the rate at which an innovation impairs existing markets affects the activity levels of the firms within the population. The model's results are validated against a matching study based on real-world data.

This paper summarizes some of the trends in the use of multi-agent technologies in economics. Multiple agent systems, fuzzy sets and neural networks are critical tools used to investigate the emerging economics research agenda related to data mining, dynamic markets stock selection and bank stress testing. This paper reviews the contributions of four such examples.