Intelligent Systems in Accounting, Finance and Management最新文献

This paper reviews some recent blockchain-based applications for information capture, distribution and preservation. As part of that review, this paper examines two key concerns with current blockchain designs for accounting and supply chain transactions: data independence and multiple semantic models for the same information distribution problem. Blockchain applications typically integrate database, application and presentation tiers all in the same ledger. This results in a general inability to query information in the ledger and other concerns. Further, since most applications appear to be private blockchain applications, there is a concern of agents needing to accommodate multiple blockchains depending on who their trading partners are and what they request. Finally, this paper uses a distributed database to design a ‘blockchain-like’ system for virtual organizations.

The profitability of trading rules evolved by three different optimised genetic programs, namely a single population genetic program (GP), a co-operative co-evolved GP, and a competitive co-evolved GP is compared. Profitability is determined by trading thirteen listed shares on the Johannesburg Stock Exchange (JSE) over a period of April 2003 to June 2008. An empirical study presented here shows that GPs can generate profitable trading rules across a variety of industries and market conditions. The results show that the co-operative co-evolved GP generates trading rules perform significantly worse than a single population GP and a competitively co-evolved GP. The results also show that a competitive co-evolved GP and the single population GP produce similar trading rules. The profits returned by the evolved trading rules are compared to the profit returned by the buy-and-hold trading strategy. The evolved trading rules significantly outperform the buy-and-hold strategy when the market trends downwards. No significant difference is identified among the buy-and-hold strategy, the competitive co-evolved GP, and single population GP when the market trends upwards.

Google's Duplex is a computer-based system with natural language capabilities that provides a human sounding conversation as it performs a set of tasks, such as making restaurant reservations. This paper analyses Google's Duplex and some of the initial reaction to the system and its capabilities. The paper does a text analysis and finds that the system-generated text creates standardized ratings that suggest the text is analytical, authentic and possesses a generally positive tone. As would be expected for the applications for which it is being used, the text is heavily focused on the present. In addition, this analysis indicates that the text provides evidence of social processes, cognitive processes, tentativeness and affiliation. Further, this paper examines some of the characteristics of speech that Duplex uses to sound human. Those capabilities appear to allow the system pass the Turing test for some well-structured tasks. However, this paper investigates some of the ethics of pretending to be human and suggests that such impersonation is against evolving computer codes of ethics.

Past efforts determining the profitability of technical analysis reached varied conclusions. We test the profitability of a composite prediction that uses buy and sell signals from technical indicators as inputs. Both machine learning methods, like neural networks, and statistical methods, like logistic regression, are used to get predictions. Inputs are signals from trend-following and mean-reversal technical indicators in addition to the variance of prices. Four representative commodities from agricultural, livestock, financial, and foreign exchange futures markets are selected to determine profitability. Special care is taken to avoid data snooping error. Both neural networks and statistical methods did not show consistent profitability.

Financial institutions are struggling with larger volume, more specific and greater frequency of regulatory reporting after the global financial crisis in 2008, especially those that need to report to multiple jurisdictions. To help to improve reporting efficiency, this paper aims to assess the existence of similarities between templates related to credit and counter party credit risk of COREP and Pillar 3 regulatory reporting frameworks by applying Correspondence Analysis and Association Rules Mining. Our results suggest a high degree of overlap between these reporting frameworks, more prominently the three business functions as Front office, Finance and Risk. These patterns can be used as guidance for financial institutions to reshape their reporting architecture.

The Euro US Dollar rate is one of the most important exchange rates in the world, making the analysis of its behavior fundamental for the global economy and for different decision-makers at both the public and private level. Furthermore, given the market efficiency of the EUR/USD exchange rate, being able to predict the rate's future short-term variation represents a great challenge. This study proposes a new framework to improve the forecasting accuracy of EUR/USD exchange rate returns through the use of an Artificial Neural Network (ANN) together with a Vector Auto Regressive (VAR) model, Vector Error Corrective model (VECM), and post-processing. The motivation lies in the integration of different approaches, which should improve the ability to forecast regarding each separate model. This is especially true given that Artificial Neural Networks are capable of capturing the short and long-term non-linear components of a time series, which VECM and VAR models are unable to do. Post-processing seeks to combine the best forecasts to make one that is better than its components. Model predictive capacity is compared according to the Root Mean Square Error (RMSE) as a loss function and its significance is analyzed using the Model Confidence Set. The results obtained show that the proposed framework outperforms the benchmark models, decreasing the RMSE of the best econometric model by 32.5% and by 19.3% the best hybrid. Thus, it is determined that forecast post-processing increases forecasting accuracy.

The primary expected use of DNA and genealogy sites has been their ability to help users find their family, find their ethnicity and to help them connect with distant relatives. In so doing such sites help users to “learn more about themselves.” Such systems have also been proposed to have the broader goals of helping connect mankind and show people how their similarities are greater than their differences. However, the use of DNA and genealogy information recently turned away from just finding family connections, ethnicity and origins. Recently it was announced that the “Golden State Killer” had been caught using information generated from using DNA and consumer genealogical websites.

This paper investigates some of the questions and unanticipated consequences raised by this alternative use of these technologies and their impact on individuals, organizations and society. As part of that analysis we analyze some of the immediate consequences on the firm from which the DNA information was gathered, the new emerging approach used by law enforcement, some privacy concerns and provide a network game formulation as a means to model user behavior. Finally, we examine some potential emerging research issues.

This paper investigates what are referred to as ‘open information transactions’. Such transactions are in contrast to traditional transactions, where typically two parties to a transaction are the only ones with information about the transaction. For example, in a sale, the seller and the purchaser typically are the only ones with information about the transaction. However, some emerging technologies, such as blockchain accounting, supply chain social media, and hashtag commerce are making information about the transactions potentially openly available to others. This paper investigates some of the implications and strategies that include the use of that open information. For example, open information in accounting and supply chain transactions provides the potential for both business intelligence analysis of the information and possibly misleading and illusory transactions, analogous to those that have garnered the recent attention of the Justice Department in cryptocurrencies. Finally, this paper suggests that blockchain transaction processing will provide reliable information in those settings where there is a “single truth” feed of information flow for the phenomena of interest, no ability to do off-blockchain transactions (or a large penalty cost) and limitation to a single identity for each enterprise on the blockchain.

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.