Intelligent Systems in Accounting, Finance and Management最新文献

This study investigates the advantage of combining the forecasting abilities of multiple generalized autoregressive conditional heteroscedasticity (GARCH)-type models, such as the standard GARCH (GARCH), exponential GARCH (eGARCH), and threshold GARCH (tGARCH) models with advanced deep learning methods to predict the volatility of five important metals (nickel, copper, tin, lead, and gold) in the Indian commodity market. This paper proposes integrating the forecasts of one to three GARCH-type models into an ensemble learning-based hybrid long short-term memory (LSTM) model to forecast commodity price volatility. We further evaluate the forecasting performance of these models for standalone LSTM and GARCH-type models using the root mean squared error, mean absolute error, and mean fundamental percentage error. The results highlight that combining the information from the forecasts of multiple GARCH types into a hybrid LSTM model leads to superior volatility forecasting capability. The SET-LSTM, which represents the model that combines forecasts of the GARCH, eGARCH, and tGARCH into the LSTM hybrid, has shown the best overall results for all metals, barring a few exceptions. Moreover, the equivalence of forecasting accuracy is tested using the Diebold–Mariano and Wilcoxon signed-rank tests.

We focus on textual analysis of the US Securities and Exchange Commission's accounting and auditing enforcement releases (AAERs). Our research question is: Did the Sarbanes–Oxley Act (SOX) 2002 affect the qualitative linguistic content of the AAERs in the post-SOX period? To answer this question, we test the null hypotheses that there will be no differences in the qualitative verbiage and sentiment of AAERs in the time periods that we study related to the enactment of SOX: pre-SOX and post-SOX. To resolve the research question, we applied several text mining methods and classification machine-learning methods. We first used two basic text-mining methods, generating a bag of words and topic modeling, for descriptive analysis of the AAER content before the enactment of SOX and after the enforcement of SOX. We then conducted sentiment analysis using four sentiment dictionaries on the content of the two time periods: before SOX and after SOX. Finally, we developed three different classification models based on well-known supervised learning algorithms and determined that SOX-related AAERs could be distinguished from non-SOX-related AAERs. Based on the results, we conclude that there were significant linguistic differences in the AAER content of the post-SOX period compared with the pre-SOX period. In other words, post-SOX-related AAERs are qualitatively different in terms of linguistic contents and sentiment values compared with the non-SOX-related AAERs.

The impending fourth industrial revolution has enhanced the role of big data analytics in today’s business practice. Consequently, many now consider big data as the most strategic resource in business to the extent that organizations that fail to utilize it may become competitively disadvantaged. Following these developments, questions have been raised about the future of the accounting discipline, especially in terms of how it can continue to add value to organizations. While some scholars have attempted to address this question, it remains an abstract concept requiring further investigation. Therefore, this study conducts a systematic literature review to determine the status of accounting research on big data analytics and provides avenues for further studies. By conducting co-occurrence network analysis on 52 peer-reviewed articles published from 2010 to 2020, three broad themes emerged, entailing big data implications for accounting practice, education, and research design. A further examination of the themes revealed few empirical studies on the phenomenon, as conceptual research dominates the field. Although external audit implications of big data are widely discussed, other accounting domains (e.g., managerial accounting and taxation) are underexplored. Therefore, future studies may focus on the implications of big data on variables such as performance measurement, information governance, tax behavior, curriculum design, and pedagogy.

Artificial intelligence (AI) in business processes and academic research in AI has significantly increased. However, the adoption of AI in organizational strategy is yet to be explored in extant literature. This study proposes two conceptual frameworks showing hierarchical relationships among the various drivers and barriers to AI adoption in organizational strategy. In a two-step approach, the literature study is first done to identify eight drivers of and nine barriers to AI adoption and validated by academic and industry experts. In the second step, MICMAC (matrice d'impacts croises-multiplication appliqúe a un classment or cross-impact matrix multiplication applied to classification) analysis categorizes the drivers and barriers to AI adoption in organizational strategy. Total interpretive structural modeling (TISM) is developed to understand the complex and hierarchical associations among the drivers and barriers. This is the first attempt to model the drivers and barriers using a methodology like TISM, which provides a comprehensive conceptual framework with hierarchical relationships and relative importance of the drivers and barriers to AI adoption. AI solutions' decision-making ability and accuracy are the most influential drivers that influence other driving factors. Lack of an AI adoption strategy, lack of AI talent, and lack of leadership commitment are the most significant barriers that affect other barriers. Recommendations for senior leadership are discussed to focus on the leading drivers and barriers. Also, the limitations and future research scope are addressed.