In Mozambique there is no evidence of a bankruptcy prediction model developed in the national economic context, yet, back in 2016, the national banking sector suffered a financial shock that resulted in Mozambique Central Bank intervention in two banks (Moza Banco, S.A. and Nosso Banco, S.A.). This was a result of the deterioration of their financial and prudential indicators, although Mozambique had been adhering to the Basel Accords since 1994. The Basel Accords provides recommendations on banking sector supervision worldwide with the aim to enhance financial system stability. While it does not predict bankruptcy, the prediction model can be used as an auxiliary tool to manage that risk, but this has to be built in the national economic context. This paper develops for Mozambique banking sector a bankruptcy prediction model in the Mozambican context through the linear discriminant analyses method, following two assumptions: (i) composition of the sample and (ii) robustness of the financial prediction indicators (the capital structure, profitability asset concentration and asset quality) from 2012 to 2020. The developed model attained an accuracy level of 84% one year before Central Bank intervention (2015) with the entire population of 19 banks of the sector, which makes it recommendable as a risk management tool for this sector.
{"title":"Development of a Bankruptcy Prediction Model for the Banking Sector in Mozambique Using Linear Discriminant Analysis","authors":"Reis Castigo Intupo","doi":"arxiv-2311.16705","DOIUrl":"https://doi.org/arxiv-2311.16705","url":null,"abstract":"In Mozambique there is no evidence of a bankruptcy prediction model developed\u0000in the national economic context, yet, back in 2016, the national banking\u0000sector suffered a financial shock that resulted in Mozambique Central Bank\u0000intervention in two banks (Moza Banco, S.A. and Nosso Banco, S.A.). This was a\u0000result of the deterioration of their financial and prudential indicators,\u0000although Mozambique had been adhering to the Basel Accords since 1994. The\u0000Basel Accords provides recommendations on banking sector supervision worldwide\u0000with the aim to enhance financial system stability. While it does not predict\u0000bankruptcy, the prediction model can be used as an auxiliary tool to manage\u0000that risk, but this has to be built in the national economic context. This\u0000paper develops for Mozambique banking sector a bankruptcy prediction model in\u0000the Mozambican context through the linear discriminant analyses method,\u0000following two assumptions: (i) composition of the sample and (ii) robustness of\u0000the financial prediction indicators (the capital structure, profitability asset\u0000concentration and asset quality) from 2012 to 2020. The developed model\u0000attained an accuracy level of 84% one year before Central Bank intervention\u0000(2015) with the entire population of 19 banks of the sector, which makes it\u0000recommendable as a risk management tool for this sector.","PeriodicalId":501372,"journal":{"name":"arXiv - QuantFin - General Finance","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138522848","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}
Ana Fernández Vilas, Rebeca P. Díaz Redondo, Daniel Couto Cancela, Alejandro Torrado Pazos
Cryptocurrencies are a type of digital money meant to provide security and anonymity while using cryptography techniques. Although cryptocurrencies represent a breakthrough and provide some important benefits, their usage poses some risks that are a result of the lack of supervising institutions and transparency. Because disinformation and volatility is discouraging for personal investors, cryptocurrencies emerged hand-in-hand with the proliferation of online users' communities and forums as places to share information that can alleviate users' mistrust. This research focuses on the study of the interplay between these cryptocurrency forums and fluctuations in cryptocurrency values. In particular, the most popular cryptocurrency Bitcoin (BTC) and a related active discussion community, Bitcointalk, are analyzed. This study shows that the activity of Bitcointalk forum keeps a direct relationship with the trend in the values of BTC, therefore analysis of this interaction would be a perfect base to support personal investments in a non-regulated market and, to confirm whether cryptocurrency forums show evidences to detect abnormal behaviors in BTC values as well as to predict or estimate these values. The experiment highlights that forum data can explain specific events in the financial field. It also underlines the relevance of quotes (regular mechanism to response a post) at periods: (1) when there is a high concentration of posts around certain topics; (2) when peaks in the BTC price are observed; and, (3) when the BTC price gradually shifts downwards and users intend to sell.
{"title":"Interplay between Cryptocurrency Transactions and Online Financial Forums","authors":"Ana Fernández Vilas, Rebeca P. Díaz Redondo, Daniel Couto Cancela, Alejandro Torrado Pazos","doi":"arxiv-2401.10238","DOIUrl":"https://doi.org/arxiv-2401.10238","url":null,"abstract":"Cryptocurrencies are a type of digital money meant to provide security and\u0000anonymity while using cryptography techniques. Although cryptocurrencies\u0000represent a breakthrough and provide some important benefits, their usage poses\u0000some risks that are a result of the lack of supervising institutions and\u0000transparency. Because disinformation and volatility is discouraging for\u0000personal investors, cryptocurrencies emerged hand-in-hand with the\u0000proliferation of online users' communities and forums as places to share\u0000information that can alleviate users' mistrust. This research focuses on the\u0000study of the interplay between these cryptocurrency forums and fluctuations in\u0000cryptocurrency values. In particular, the most popular cryptocurrency Bitcoin\u0000(BTC) and a related active discussion community, Bitcointalk, are analyzed.\u0000This study shows that the activity of Bitcointalk forum keeps a direct\u0000relationship with the trend in the values of BTC, therefore analysis of this\u0000interaction would be a perfect base to support personal investments in a\u0000non-regulated market and, to confirm whether cryptocurrency forums show\u0000evidences to detect abnormal behaviors in BTC values as well as to predict or\u0000estimate these values. The experiment highlights that forum data can explain\u0000specific events in the financial field. It also underlines the relevance of\u0000quotes (regular mechanism to response a post) at periods: (1) when there is a\u0000high concentration of posts around certain topics; (2) when peaks in the BTC\u0000price are observed; and, (3) when the BTC price gradually shifts downwards and\u0000users intend to sell.","PeriodicalId":501372,"journal":{"name":"arXiv - QuantFin - General Finance","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139515218","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}
This research paper focuses on the integration of Artificial Intelligence (AI) into the currency trading landscape, positing the development of personalized AI models, essentially functioning as intelligent personal assistants tailored to the idiosyncrasies of individual traders. The paper posits that AI models are capable of identifying nuanced patterns within the trader's historical data, facilitating a more accurate and insightful assessment of psychological risk dynamics in currency trading. The PRI is a dynamic metric that experiences fluctuations in response to market conditions that foster psychological fragility among traders. By employing sophisticated techniques, a classifying decision tree is crafted, enabling clearer decision-making boundaries within the tree structure. By incorporating the user's chronological trade entries, the model becomes adept at identifying critical junctures when psychological risks are heightened. The real-time nature of the calculations enhances the model's utility as a proactive tool, offering timely alerts to traders about impending moments of psychological risks. The implications of this research extend beyond the confines of currency trading, reaching into the realms of other industries where the judicious application of personalized modeling emerges as an efficient and strategic approach. This paper positions itself at the intersection of cutting-edge technology and the intricate nuances of human psychology, offering a transformative paradigm for decision making support in dynamic and high-pressure environments.
{"title":"Decision Tree Psychological Risk Assessment in Currency Trading","authors":"Jai Pal","doi":"arxiv-2311.15222","DOIUrl":"https://doi.org/arxiv-2311.15222","url":null,"abstract":"This research paper focuses on the integration of Artificial Intelligence\u0000(AI) into the currency trading landscape, positing the development of\u0000personalized AI models, essentially functioning as intelligent personal\u0000assistants tailored to the idiosyncrasies of individual traders. The paper\u0000posits that AI models are capable of identifying nuanced patterns within the\u0000trader's historical data, facilitating a more accurate and insightful\u0000assessment of psychological risk dynamics in currency trading. The PRI is a\u0000dynamic metric that experiences fluctuations in response to market conditions\u0000that foster psychological fragility among traders. By employing sophisticated\u0000techniques, a classifying decision tree is crafted, enabling clearer\u0000decision-making boundaries within the tree structure. By incorporating the\u0000user's chronological trade entries, the model becomes adept at identifying\u0000critical junctures when psychological risks are heightened. The real-time\u0000nature of the calculations enhances the model's utility as a proactive tool,\u0000offering timely alerts to traders about impending moments of psychological\u0000risks. The implications of this research extend beyond the confines of currency\u0000trading, reaching into the realms of other industries where the judicious\u0000application of personalized modeling emerges as an efficient and strategic\u0000approach. This paper positions itself at the intersection of cutting-edge\u0000technology and the intricate nuances of human psychology, offering a\u0000transformative paradigm for decision making support in dynamic and\u0000high-pressure environments.","PeriodicalId":501372,"journal":{"name":"arXiv - QuantFin - General Finance","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138522840","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}
This study employs machine learning models to predict the failure of Peer-to-Peer (P2P) lending platforms, specifically in China. By employing the filter method and wrapper method with forward selection and backward elimination, we establish a rigorous and practical procedure that ensures the robustness and importance of variables in predicting platform failures. The research identifies a set of robust variables that consistently appear in the feature subsets across different selection methods and models, suggesting their reliability and relevance in predicting platform failures. The study highlights that reducing the number of variables in the feature subset leads to an increase in the false acceptance rate while the performance metrics remain stable, with an AUC value of approximately 0.96 and an F1 score of around 0.88. The findings of this research provide significant practical implications for regulatory authorities and investors operating in the Chinese P2P lending industry.
{"title":"Predicting Failure of P2P Lending Platforms through Machine Learning: The Case in China","authors":"Jen-Yin Yeh, Hsin-Yu Chiu, Jhih-Huei Huang","doi":"arxiv-2311.14577","DOIUrl":"https://doi.org/arxiv-2311.14577","url":null,"abstract":"This study employs machine learning models to predict the failure of\u0000Peer-to-Peer (P2P) lending platforms, specifically in China. By employing the\u0000filter method and wrapper method with forward selection and backward\u0000elimination, we establish a rigorous and practical procedure that ensures the\u0000robustness and importance of variables in predicting platform failures. The\u0000research identifies a set of robust variables that consistently appear in the\u0000feature subsets across different selection methods and models, suggesting their\u0000reliability and relevance in predicting platform failures. The study highlights\u0000that reducing the number of variables in the feature subset leads to an\u0000increase in the false acceptance rate while the performance metrics remain\u0000stable, with an AUC value of approximately 0.96 and an F1 score of around 0.88.\u0000The findings of this research provide significant practical implications for\u0000regulatory authorities and investors operating in the Chinese P2P lending\u0000industry.","PeriodicalId":501372,"journal":{"name":"arXiv - QuantFin - General Finance","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138542598","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}
Sovereign loan portfolios of Multilateral Development Banks (MDBs) typically consist of only a small number of borrowers and hence are heavily exposed to single name concentration risk. Based on realistic MDB portfolios constructed from publicly available data, this paper quantifies the magnitude of the exposure to name concentration risk using exact Monte Carlo simulations. In comparing the exact adjustment for name concentration risk to its analytic approximation as currently applied by the major rating agency Standard & Poor's, we further investigate whether current capital adequacy frameworks for MDBs are overly conservative. Finally, we discuss the choice of appropriate model parameters and their impact on measures of name concentration risk.
{"title":"On the Relevance and Appropriateness of Name Concentration Risk Adjustments for Portfolios of Multilateral Development Banks","authors":"Eva Lütkebohmert, Julian Sester, Hongyi Shen","doi":"arxiv-2311.13802","DOIUrl":"https://doi.org/arxiv-2311.13802","url":null,"abstract":"Sovereign loan portfolios of Multilateral Development Banks (MDBs) typically\u0000consist of only a small number of borrowers and hence are heavily exposed to\u0000single name concentration risk. Based on realistic MDB portfolios constructed\u0000from publicly available data, this paper quantifies the magnitude of the\u0000exposure to name concentration risk using exact Monte Carlo simulations. In\u0000comparing the exact adjustment for name concentration risk to its analytic\u0000approximation as currently applied by the major rating agency Standard &\u0000Poor's, we further investigate whether current capital adequacy frameworks for\u0000MDBs are overly conservative. Finally, we discuss the choice of appropriate\u0000model parameters and their impact on measures of name concentration risk.","PeriodicalId":501372,"journal":{"name":"arXiv - QuantFin - General Finance","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138522773","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}
This research delves into the intricacies of Bitcoin, a decentralized peer-to-peer network, and its associated blockchain, which records all transactions since its inception. While this ensures integrity and transparency, the transparent nature of Bitcoin potentially compromises users' privacy rights. To address this concern, users have adopted CoinJoin, a method that amalgamates multiple transaction intents into a single, larger transaction to bolster transactional privacy. This process complicates individual transaction tracing and disrupts many established blockchain analysis heuristics. Despite its significance, limited research has been conducted on identifying CoinJoin transactions. Particularly noteworthy are varied CoinJoin implementations such as JoinMarket, Wasabi, and Whirlpool, each presenting distinct challenges due to their unique transaction structures. This study delves deeply into the open-source implementations of these protocols, aiming to develop refined heuristics for identifying their transactions on the blockchain. Our exhaustive analysis covers transactions up to block 760,000, offering a comprehensive insight into CoinJoin transactions and their implications for Bitcoin blockchain analysis.
{"title":"Heuristics for Detecting CoinJoin Transactions on the Bitcoin Blockchain","authors":"Hugo Schnoering, Michalis Vazirgiannis","doi":"arxiv-2311.12491","DOIUrl":"https://doi.org/arxiv-2311.12491","url":null,"abstract":"This research delves into the intricacies of Bitcoin, a decentralized\u0000peer-to-peer network, and its associated blockchain, which records all\u0000transactions since its inception. While this ensures integrity and\u0000transparency, the transparent nature of Bitcoin potentially compromises users'\u0000privacy rights. To address this concern, users have adopted CoinJoin, a method\u0000that amalgamates multiple transaction intents into a single, larger transaction\u0000to bolster transactional privacy. This process complicates individual\u0000transaction tracing and disrupts many established blockchain analysis\u0000heuristics. Despite its significance, limited research has been conducted on\u0000identifying CoinJoin transactions. Particularly noteworthy are varied CoinJoin\u0000implementations such as JoinMarket, Wasabi, and Whirlpool, each presenting\u0000distinct challenges due to their unique transaction structures. This study\u0000delves deeply into the open-source implementations of these protocols, aiming\u0000to develop refined heuristics for identifying their transactions on the\u0000blockchain. Our exhaustive analysis covers transactions up to block 760,000,\u0000offering a comprehensive insight into CoinJoin transactions and their\u0000implications for Bitcoin blockchain analysis.","PeriodicalId":501372,"journal":{"name":"arXiv - QuantFin - General Finance","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138542562","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}
We use empirical Bayes (EB) to mine for out-of-sample returns among 73,108 long-short strategies constructed from accounting ratios, past returns, and ticker symbols. EB predicts returns are concentrated in accounting and past return strategies, small stocks, and pre-2004 samples. The cross-section of out-of-sample return lines up closely with EB predictions. Data-mined portfolios have mean returns comparable with published portfolios, but the data-mined returns are arguably free of data mining bias. In contrast, controlling for multiple testing following Harvey, Liu, and Zhu (2016) misses the vast majority of returns. This "high-throughput asset pricing" provides an evidence-based solution for data mining bias.
我们使用经验贝叶斯(EB)从会计比率、过去收益和股票代码构建的73,108个多空策略中挖掘样本外收益。EB预测的回报集中在会计和过去的回报策略、小股和2004年以前的样本上。样本外回报的横截面与EB预测密切相关。数据挖掘的投资组合具有与已发布的投资组合相当的平均回报，但数据挖掘的回报可以说没有数据挖掘的偏见。相比之下，在Harvey, Liu, and Zhu(2016)之后，控制多重测试错过了绝大多数回报。这种“高通量资产定价”为数据挖掘偏见提供了一种基于证据的解决方案。
{"title":"High-Throughput Asset Pricing","authors":"Andrew Y. Chen, Chukwuma Dim","doi":"arxiv-2311.10685","DOIUrl":"https://doi.org/arxiv-2311.10685","url":null,"abstract":"We use empirical Bayes (EB) to mine for out-of-sample returns among 73,108\u0000long-short strategies constructed from accounting ratios, past returns, and\u0000ticker symbols. EB predicts returns are concentrated in accounting and past\u0000return strategies, small stocks, and pre-2004 samples. The cross-section of\u0000out-of-sample return lines up closely with EB predictions. Data-mined\u0000portfolios have mean returns comparable with published portfolios, but the\u0000data-mined returns are arguably free of data mining bias. In contrast,\u0000controlling for multiple testing following Harvey, Liu, and Zhu (2016) misses\u0000the vast majority of returns. This \"high-throughput asset pricing\" provides an\u0000evidence-based solution for data mining bias.","PeriodicalId":501372,"journal":{"name":"arXiv - QuantFin - General Finance","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138522789","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}
Banks' performance is an important topic for both professionals and researchers. Given the important literature on this subject, this paper aims to bring an up-to-date and organized review of literature on the determinants of banks performance. This paper discusses the main approaches that molded the debate on banks performance and their main determinants. An in-depth understanding of these latter may allow on the one hand, bank managers and regulators to improve the sector efficiency and to deal with the new trends shaping the future of their industry and on the other hand, academicians to enrich research and knowledge on this field. Through the analysis of 54 studies published in 42 peer-reviewed journals, we show that despite the importance of the existent literature, the subject of bank performance factors did not reveal all its secrets and still constitute a fertile field for critical debates, especially since the COVID-19 and the increasingly pressing rise in power of digital transformation and artificial intelligence in general and FinTechs in particular. The study concludes by suggesting new promising research avenues.
{"title":"Bank Performance Determinants: State of the Art and Future Research Avenues","authors":"Anas Azzabi, Younes Lahrichi","doi":"arxiv-2311.08617","DOIUrl":"https://doi.org/arxiv-2311.08617","url":null,"abstract":"Banks' performance is an important topic for both professionals and\u0000researchers. Given the important literature on this subject, this paper aims to\u0000bring an up-to-date and organized review of literature on the determinants of\u0000banks performance. This paper discusses the main approaches that molded the\u0000debate on banks performance and their main determinants. An in-depth\u0000understanding of these latter may allow on the one hand, bank managers and\u0000regulators to improve the sector efficiency and to deal with the new trends\u0000shaping the future of their industry and on the other hand, academicians to\u0000enrich research and knowledge on this field. Through the analysis of 54 studies\u0000published in 42 peer-reviewed journals, we show that despite the importance of\u0000the existent literature, the subject of bank performance factors did not reveal\u0000all its secrets and still constitute a fertile field for critical debates,\u0000especially since the COVID-19 and the increasingly pressing rise in power of\u0000digital transformation and artificial intelligence in general and FinTechs in\u0000particular. The study concludes by suggesting new promising research avenues.","PeriodicalId":501372,"journal":{"name":"arXiv - QuantFin - General Finance","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138523219","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}
The auditor work is examining that a company's financial statements faithfully reflect its financial situation. His wage, the audit fees, are not fixed among all companies, but can be affected by the financial and structural characteristics of the company, as well as the characteristics of the firm he belongs to. Another factor that may affect his wage in an auditor switching, which can be resulted from changes in the company that may influence the fees. This paper examines the effect nature of the auditor switching on his wage, and the factors of the company characteristics and the economy data which determine the wage at switching. A product of the research are tools for predicting and evaluating the auditor wage at switching. These tools are important for the auditor himself, but also for the company manager to correctly determine the wage due to the possibility that the quality of the audit work depends on its fees. Two main results are obtained. First, the direction of the wage change in the switching year depends on the economic stability of the economy. Second, the switching effect on the direction and the change size in wage depends on the change size in the company characteristics before and after switching - a large change versus a stable one. We get that forecasting the change size in wage for companies with a larger change is their characteristics is paralleled to forecasting a wage increasing. And vice versa, forecasting the change size in wage for companies with a stable change in their characteristics is paralleled to forecasting a wage decreasing. But, whereas the former can be achieved based on the company characteristics and macroeconomics factors, the predictably of these characteristics and factors is negligible for the letter.
{"title":"Audit fees in auditor switching","authors":"Sarit Agami","doi":"arxiv-2311.08250","DOIUrl":"https://doi.org/arxiv-2311.08250","url":null,"abstract":"The auditor work is examining that a company's financial statements\u0000faithfully reflect its financial situation. His wage, the audit fees, are not\u0000fixed among all companies, but can be affected by the financial and structural\u0000characteristics of the company, as well as the characteristics of the firm he\u0000belongs to. Another factor that may affect his wage in an auditor switching,\u0000which can be resulted from changes in the company that may influence the fees.\u0000This paper examines the effect nature of the auditor switching on his wage, and\u0000the factors of the company characteristics and the economy data which determine\u0000the wage at switching. A product of the research are tools for predicting and\u0000evaluating the auditor wage at switching. These tools are important for the\u0000auditor himself, but also for the company manager to correctly determine the\u0000wage due to the possibility that the quality of the audit work depends on its\u0000fees. Two main results are obtained. First, the direction of the wage change in\u0000the switching year depends on the economic stability of the economy. Second,\u0000the switching effect on the direction and the change size in wage depends on\u0000the change size in the company characteristics before and after switching - a\u0000large change versus a stable one. We get that forecasting the change size in\u0000wage for companies with a larger change is their characteristics is paralleled\u0000to forecasting a wage increasing. And vice versa, forecasting the change size\u0000in wage for companies with a stable change in their characteristics is\u0000paralleled to forecasting a wage decreasing. But, whereas the former can be\u0000achieved based on the company characteristics and macroeconomics factors, the\u0000predictably of these characteristics and factors is negligible for the letter.","PeriodicalId":501372,"journal":{"name":"arXiv - QuantFin - General Finance","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138522785","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}
Machine learning and deep learning have become increasingly prevalent in financial prediction and forecasting tasks, offering advantages such as enhanced customer experience, democratising financial services, improving consumer protection, and enhancing risk management. However, these complex models often lack transparency and interpretability, making them challenging to use in sensitive domains like finance. This has led to the rise of eXplainable Artificial Intelligence (XAI) methods aimed at creating models that are easily understood by humans. Classical XAI methods, such as LIME and SHAP, have been developed to provide explanations for complex models. While these methods have made significant contributions, they also have limitations, including computational complexity, inherent model bias, sensitivity to data sampling, and challenges in dealing with feature dependence. In this context, this paper explores good practices for deploying explainability in AI-based systems for finance, emphasising the importance of data quality, audience-specific methods, consideration of data properties, and the stability of explanations. These practices aim to address the unique challenges and requirements of the financial industry and guide the development of effective XAI tools.
{"title":"A Hypothesis on Good Practices for AI-based Systems for Financial Time Series Forecasting: Towards Domain-Driven XAI Methods","authors":"Branka Hadji Misheva, Joerg Osterrieder","doi":"arxiv-2311.07513","DOIUrl":"https://doi.org/arxiv-2311.07513","url":null,"abstract":"Machine learning and deep learning have become increasingly prevalent in\u0000financial prediction and forecasting tasks, offering advantages such as\u0000enhanced customer experience, democratising financial services, improving\u0000consumer protection, and enhancing risk management. However, these complex\u0000models often lack transparency and interpretability, making them challenging to\u0000use in sensitive domains like finance. This has led to the rise of eXplainable\u0000Artificial Intelligence (XAI) methods aimed at creating models that are easily\u0000understood by humans. Classical XAI methods, such as LIME and SHAP, have been\u0000developed to provide explanations for complex models. While these methods have\u0000made significant contributions, they also have limitations, including\u0000computational complexity, inherent model bias, sensitivity to data sampling,\u0000and challenges in dealing with feature dependence. In this context, this paper\u0000explores good practices for deploying explainability in AI-based systems for\u0000finance, emphasising the importance of data quality, audience-specific methods,\u0000consideration of data properties, and the stability of explanations. These\u0000practices aim to address the unique challenges and requirements of the\u0000financial industry and guide the development of effective XAI tools.","PeriodicalId":501372,"journal":{"name":"arXiv - QuantFin - General Finance","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138522781","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：