Intelligent Systems in Accounting, Finance and Management最新文献_第2页

Cost-sensitive machine learning to support startup investment decisions 成本敏感型机器学习为初创企业投资决策提供支持

Intelligent Systems in Accounting, Finance and Management Pub Date : 2024-02-13 DOI: 10.1002/isaf.1548

Ronald Setty, Yuval Elovici, Dafna Schwartz

{"title":"Cost-sensitive machine learning to support startup investment decisions","authors":"Ronald Setty, Yuval Elovici, Dafna Schwartz","doi":"10.1002/isaf.1548","DOIUrl":"https://doi.org/10.1002/isaf.1548","url":null,"abstract":"<p>In 2022, global startup investments exceeded US$445 billion, sourced from entities like venture capital (VC) funds, angel investors, and equity crowdfunding. Despite their role in driving innovation, startup investments often fall short of S&P 500 returns. Surprisingly, the potential of artificial intelligence (AI) remains untapped by investors, despite AI's growing sway in financial decision-making. Our empirical analysis predicts the success of 10,000 Israeli startups, utilizing diverse machine learning models. Unlike prior research, we employ the MetaCost algorithm to convert models into cost-sensitive variants, minimizing total cost instead of total error. This innovative approach enables varied costs linked to different prediction errors. Our results underscore that these cost-sensitive machine learning models significantly reduce risk for VC funds and startup investors compared to traditional ones. Furthermore, these models provide investors with a distinct capability to tailor their risk profiles, aligning predictions with their risk appetite. However, while cost-sensitive machine learning reduces risk, it may limit potential gains by predicting fewer successful startups. To address this, we propose methods to enhance successful startup identification, including aggregating outcomes from multiple MetaCost models, particularly advantageous for smaller deal flows. Our research advances AI's role in startup investing, presenting a pivotal tool for investors navigating this domain.</p>","PeriodicalId":53473,"journal":{"name":"Intelligent Systems in Accounting, Finance and Management","volume":"31 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/isaf.1548","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139732302","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Using large language models to write theses and dissertations 使用大型语言模型撰写论文和学位论文

Intelligent Systems in Accounting, Finance and Management Pub Date : 2023-12-20 DOI: 10.1002/isaf.1547

Daniel E. O'Leary

引用次数: 0

Costs associated with exit or disposal activities: A topic modeling investigation of disclosure and market reaction 与退出或处置活动相关的成本：对信息披露和市场反应的专题建模调查

Intelligent Systems in Accounting, Finance and Management Pub Date : 2023-12-06 DOI: 10.1002/isaf.1545

Charles P. Cullinan, Richard Holowczak, David Louton, Hakan Saraoglu

{"title":"Costs associated with exit or disposal activities: A topic modeling investigation of disclosure and market reaction","authors":"Charles P. Cullinan, Richard Holowczak, David Louton, Hakan Saraoglu","doi":"10.1002/isaf.1545","DOIUrl":"10.1002/isaf.1545","url":null,"abstract":"<div>\u0000 \u0000 <p>The Securities and Exchange Commission (SEC) mandates disclosure of exit or disposal activity events in 8-K filings. We use Latent Dirichlet Allocation (LDA), a topic modeling method from computational linguistics, to investigate the possibility that substantively different event types may be subsumed under Item 2.05, the SEC category for costs associated with exit or disposal activities. Our analysis reveals that four distinct topics are reported under the Item 2.05 umbrella category: (1) restructuring, (2) disposal of a line of business, (3) plant closings, and (4) layoffs/workforce reductions. We then investigate various aspects of these 8-K filings. We find that the market reacts most negatively to workforce reductions that are reported in the absence of a broader strategic initiative. Subsequent amendments to the Item 2.05 8-K filings are significantly more likely for restructuring initiatives, and significantly less likely for layoffs. Asset impairment charges most frequently accompany line-of-business disposals and plant closings. Our results demonstrate that there are meaningful differences between the event types reported within Item 2.05 filings and that LDA provides a useful means of differentiating among these event types.</p>\u0000 </div>","PeriodicalId":53473,"journal":{"name":"Intelligent Systems in Accounting, Finance and Management","volume":"30 4","pages":"173-191"},"PeriodicalIF":0.0,"publicationDate":"2023-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138597223","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Cryptoassets: Definitions and accounting treatment under the current International Financial Reporting Standards framework 加密资产：现行《国际财务报告准则》框架下的定义和会计处理方法

Intelligent Systems in Accounting, Finance and Management Pub Date : 2023-12-06 DOI: 10.1002/isaf.1543

Luz Parrondo

引用次数: 0

Exploring the time-frequency connectedness among non-fungible tokens and developed stock markets 探索不可流通代币与发达股票市场之间的时间频率关联性

Intelligent Systems in Accounting, Finance and Management Pub Date : 2023-11-23 DOI: 10.1002/isaf.1544

Wael Hemrit, Noureddine Benlagha, Racha Ben Arous, Mounira Ben Arab

{"title":"Exploring the time-frequency connectedness among non-fungible tokens and developed stock markets","authors":"Wael Hemrit, Noureddine Benlagha, Racha Ben Arous, Mounira Ben Arab","doi":"10.1002/isaf.1544","DOIUrl":"10.1002/isaf.1544","url":null,"abstract":"<div>\u0000 \u0000 <p>In this paper, we examine the connectedness between volatilities for various non-fungible tokens (NFTs) and developed stock markets during the period from July 1, 2018, to June 15, 2022. With the use of the time-varying connectedness methods to explore the volatility interdependences among these assets, we find that there is a significant volatility connectedness during Russia's invasion of Ukraine and COVID-19 periods. Evidence emerging from this study advocates the inclusion of NFTs in developed stock markets for medium and long time periods only. The results also suggest that UK and Germany stock markets are the predominant market of spillover transmission, whereas the XTZ is the top net recipient/transmitter of volatility connectedness shocks. Moreover, Chinese stock market and ENJ offer more diversification gains than others, and the volatility connectedness from US stock market to NFTs is more pronounced in the long-term than the short-term. Our research provides some urgent and prominent insights to help investors and policymakers to be aware that NFTs are important hedge assets that should be added to stock portfolios during periods of geopolitical stability and in the post-pandemic times.</p>\u0000 </div>","PeriodicalId":53473,"journal":{"name":"Intelligent Systems in Accounting, Finance and Management","volume":"30 4","pages":"192-207"},"PeriodicalIF":0.0,"publicationDate":"2023-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138822544","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An application of artificial neural networks in corporate social responsibility decision making 人工神经网络在企业社会责任决策中的应用

Intelligent Systems in Accounting, Finance and Management Pub Date : 2023-10-03 DOI: 10.1002/isaf.1542

Nguyen Thi Thanh Binh

引用次数: 0

Enterprise large language models: Knowledge characteristics, risks, and organizational activities 企业大型语言模型：知识特征、风险和组织活动

Intelligent Systems in Accounting, Finance and Management Pub Date : 2023-09-25 DOI: 10.1002/isaf.1541

Daniel E. O'Leary

引用次数: 0

Remarks on a copula-based conditional value at risk for the portfolio problem 关于投资组合问题的一个基于copula的条件风险值的注记

Intelligent Systems in Accounting, Finance and Management Pub Date : 2023-08-07 DOI: 10.1002/isaf.1540

Andres Mauricio Molina Barreto, Naoyuki Ishimura

引用次数: 0

An efficient graph-based peer selection method for financial statements 一种高效的基于图的财务报表对等选择方法

Intelligent Systems in Accounting, Finance and Management Pub Date : 2023-07-05 DOI: 10.1002/isaf.1539

Sander Noels, Simon De Ridder, Sébastien Viaene, Tijl De Bie

引用次数: 0

Evaluating interpretable machine learning predictions for cryptocurrencies 评估加密货币的可解释机器学习预测

Intelligent Systems in Accounting, Finance and Management Pub Date : 2023-06-21 DOI: 10.1002/isaf.1538

Ahmad El Majzoub, Fethi A. Rabhi, Walayat Hussain

{"title":"Evaluating interpretable machine learning predictions for cryptocurrencies","authors":"Ahmad El Majzoub, Fethi A. Rabhi, Walayat Hussain","doi":"10.1002/isaf.1538","DOIUrl":"https://doi.org/10.1002/isaf.1538","url":null,"abstract":"<p>This study explores various machine learning and deep learning applications on financial data modelling, analysis and prediction processes. The main focus is to test the prediction accuracy of cryptocurrency hourly returns and to explore, analyse and showcase the various interpretability features of the ML models. The study considers the six most dominant cryptocurrencies in the market: Bitcoin, Ethereum, Binance Coin, Cardano, Ripple and Litecoin. The experimental settings explore the formation of the corresponding datasets from technical, fundamental and statistical analysis. The paper compares various existing and enhanced algorithms and explains their results, features and limitations. The algorithms include decision trees, random forests and ensemble methods, SVM, neural networks, single and multiple features N-BEATS, ARIMA and Google AutoML. From experimental results, we see that predicting cryptocurrency returns is possible. However, prediction algorithms may not generalise for different assets and markets over long periods. There is no clear winner that satisfies all requirements, and the main choice of algorithm will be tied to the user needs and provided resources.</p>","PeriodicalId":53473,"journal":{"name":"Intelligent Systems in Accounting, Finance and Management","volume":"30 3","pages":"137-149"},"PeriodicalIF":0.0,"publicationDate":"2023-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/isaf.1538","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"50153077","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0