Intelligent Systems in Accounting, Finance and Management最新文献

{"title":"Balanced Underbagged Ensemble Approach for Classifying Highly Imbalanced Datasets in the Insurance and Financial Sectors","authors":"Alberto Gutierrez-Gallego,&nbsp;Oscar Garnica,&nbsp;Daniel Parra,&nbsp;J. Manuel Velasco,&nbsp;J. Ignacio Hidalgo","doi":"10.1002/isaf.70018","DOIUrl":"https://doi.org/10.1002/isaf.70018","url":null,"abstract":"<p>Data bias is a critical challenge in machine learning applications within the financial and insurance sectors, as it can lead to misleading risk assessments and inaccurate predictive models. A prevalent source of bias in real-world datasets is the imbalanced distribution of classes, which is particularly problematic in fraud detection, credit risk assessment, and claim prediction. Traditional approaches to handling imbalanced data often rely on undersampling or oversampling techniques. However, these methods may generate unrealistic minority class samples or fail to perform effectively when dealing with extreme class imbalances. In this paper, we propose a configurable technique based on the underbagging method, integrated with a classifier for highly imbalanced datasets. Our approach is designed to enhance the predictive accuracy of the minority class while maintaining robust performance for the majority class. We incorporate our methodology into a classification ensemble framework and evaluate its effectiveness by comparing it against 100 combinations of 10 different oversampling and undersampling techniques applied to 10 different machine learning algorithms. The evaluation is conducted on two highly imbalanced real-world datasets: one related to auto insurance claims and another focused on credit card fraud detection. Our statistical analysis demonstrates that Balanced Underbagged Ensemble achieves superior classification performance in terms of recall for both classes, regardless of the base machine learning model used within the ensemble. Furthermore, our method finds an optimal balance between classification performance and computational efficiency.</p>","PeriodicalId":53473,"journal":{"name":"Intelligent Systems in Accounting, Finance and Management","volume":"32 4","pages":""},"PeriodicalIF":3.7,"publicationDate":"2025-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/isaf.70018","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145272973","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}

{"title":"Lost in the Modeling Stage: A Comparative Analysis of Machine Learning Models for Real Estate Data","authors":"Ian Lenaers,&nbsp;Lieven De Moor","doi":"10.1002/isaf.70019","DOIUrl":"https://doi.org/10.1002/isaf.70019","url":null,"abstract":"<div>\u0000 \u0000 <p>Machine learning dominates automated property valuation, yet comprehensive comparisons of predictive models remain scarce. This study compares 28 rent prediction models using 79,735 Belgian residential rental properties from 2022. Predictive performance is evaluated with traditional and alternative metrics for train data, test data, and across deciles. The results confirm that tree-based ensemble models outperform others, with stacking and averaging yielding superior results at a higher computational cost. Furthermore, middle-range rents show better predictive accuracy than extremes. Traditional and alternative metrics provide consistent findings. These insights aid real estate stakeholders seeking to enhance their expert systems for real estate price modeling.</p>\u0000 </div>","PeriodicalId":53473,"journal":{"name":"Intelligent Systems in Accounting, Finance and Management","volume":"32 4","pages":""},"PeriodicalIF":3.7,"publicationDate":"2025-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145272747","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}

{"title":"Understanding Decision-Making to Tackle Complexity in Open Innovation Labs in Government","authors":"Ben De Coninck,&nbsp;Stijn Viaene,&nbsp;Jan Leysen","doi":"10.1002/isaf.70017","DOIUrl":"https://doi.org/10.1002/isaf.70017","url":null,"abstract":"<div>\u0000 \u0000 <p>This article examines the decision-making processes in open innovation labs (OI-labs) in government. Through a qualitative single case study, we explore how the use of causal and effectual reasoning, as dichotomous logics, evolves over time and is manifested in the form of organizational practices to tackle temporal, relational, and cultural complexity. The findings reveal three episodes: the conceptualizing of the lab (predominantly causation), the building of the lab (predominantly effectuation), and the sustaining of the lab (hybrid causation–effectuation). Moreover, shifts in the logic are aimed at addressing different types of complexity, and over time, a hybrid logic emerges.</p>\u0000 </div>","PeriodicalId":53473,"journal":{"name":"Intelligent Systems in Accounting, Finance and Management","volume":"32 3","pages":""},"PeriodicalIF":3.7,"publicationDate":"2025-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145038289","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}

{"title":"FinSentiment: Predicting Financial Sentiment Through Transfer Learning","authors":"Zehra Erva Ergun,&nbsp;Emre Sefer","doi":"10.1002/isaf.70015","DOIUrl":"https://doi.org/10.1002/isaf.70015","url":null,"abstract":"<div>\u0000 \u0000 <p>There is an increasing interest in financial text mining tasks. Significant progress has been made by using deep learning-based models on a generic corpus, which also shows reasonable results on financial text mining tasks such as financial sentiment analysis. However, financial sentiment analysis is still demanding work because of the insufficiency of labeled data for the financial domain and its specialized language. General-purpose deep learning methods are not as effective mainly due to specialized language used in the financial context. In this study, we focus on enhancing the performance of financial text mining tasks by improving the existing pretrained language models via NLP transfer learning. Pretrained language models demand a small quantity of labeled samples, and they could be enhanced to a greater extent by training them on domain-specific corpora instead. We propose an enhanced model FinSentiment, which incorporates enhanced versions of a number of recently proposed pretrained models, such as BERT, XLNet, RoBERTa, GPT, Llama, and T5, to better perform across NLP tasks in financial domain by training these models on financial domain corpora. The corresponding finance-specific models in FinSentiment are called Fin-BERT, Fin-XLNet, Fin-RoBERTa, Fin-GPT, Fin-Llama, and Fin-T5, respectively. We also propose variants of these models jointly trained over financial domain and general corpora. Our finance-specific FinSentiment models, in general, show the best performance across three financial sentiment analysis datasets, even when only a subpart of these models is fine-tuned with a smaller training set. Our results exhibit enhancement for each tested performance criteria on the existing results for these datasets. Extensive experimental results demonstrate the effectiveness and robustness of especially RoBERTa pretrained on financial corpora. Overall, we show that NLP transfer learning techniques are favorable solutions to financial sentiment analysis tasks. Our source code has been deposited at https://github.com/seferlab/finsentiment.</p>\u0000 </div>","PeriodicalId":53473,"journal":{"name":"Intelligent Systems in Accounting, Finance and Management","volume":"32 3","pages":""},"PeriodicalIF":3.7,"publicationDate":"2025-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145037646","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}

{"title":"Manual Journal Entry Testing: Integrating Natural Language Processing and Deep Learning","authors":"Qing Huang,&nbsp;Huijue Kelly Duan,&nbsp;Miklos A. Vasarhelyi","doi":"10.1002/isaf.70016","DOIUrl":"https://doi.org/10.1002/isaf.70016","url":null,"abstract":"<div>\u0000 \u0000 <p>This paper presents an innovative approach to comprehensively and systematically evaluate manual journal entries (MJEs) and enhance the control procedures in auditing. The proposed approach combines quantitative and qualitative information to develop various Key Risk Indicators (KRIs) that provide insights into potential risks associated with MJEs. The approach incorporates textual analytics into traditional quantitative measures. Using the data obtained from a multinational company, the application of the proposed testing approach demonstrates its effectiveness in identifying potential high-risk MJEs and improving the company's journal entry testing and monitoring procedures. The findings contribute to current audit practices by offering a more efficient and comprehensive method for evaluating MJEs.</p>\u0000 </div>","PeriodicalId":53473,"journal":{"name":"Intelligent Systems in Accounting, Finance and Management","volume":"32 3","pages":""},"PeriodicalIF":3.7,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144935038","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}

{"title":"Prediction of Volatility Using Monetary Rate and GARCH-LSTM Hybrid Model","authors":"Jyoti Ranjan,&nbsp;C. Anirvinna","doi":"10.1002/isaf.70013","DOIUrl":"https://doi.org/10.1002/isaf.70013","url":null,"abstract":"<div>\u0000 \u0000 <p>Predicting volatility is very important for the financial markets as it helps to determine risk and decision-making. Predicting volatilities for such stock indices, which include the Nifty 50, is important for traders, investors, and policymakers. In this study, advanced hybrid models are used to predict the volatility of the Nifty 50 index over intervals of 1, 7, 14, and 21 days. The GJR-GARCH-LSTM and the GARCH-LSTM are two hybrid models that forecast the volatility of the Nifty 50. The effect of including the cash reserve ratio (CRR) in the analysis is also looked at. As the forecast horizon grows, the results show decreased prediction accuracy. The mean squared error (MSE) increased by 0.78% from the 1-day to the 7-day forecast, decreased by 2.63% between the 1-day and 7-day projections, rose by about 55% from the 7-day to the 14-day forecast, and grew by 56% between the 14-day and 21-day projections. The GJR-GARCH-LSTM model had better results compared to the simple GARCH-LSTM hybrid model. The novelty of this study is in building and validating hybrid models, specifically the GJR-GARCH-LSTM, to predict Nifty 50 index volatility and using the CRR as a macroeconomic explanatory variable. Different from current literature, which tends to use hybrid models in a generic sense, this paper adapts the model to the Indian financial environment and shows the additional predictive power of monetary policy determinants such as CRR.</p>\u0000 </div>","PeriodicalId":53473,"journal":{"name":"Intelligent Systems in Accounting, Finance and Management","volume":"32 3","pages":""},"PeriodicalIF":3.7,"publicationDate":"2025-08-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144758617","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}

{"title":"Developing an Accounting Virtual Assistant Through Supervised Fine-Tuning (SFT) of a Small Language Model (SLM)","authors":"Mario Zupan","doi":"10.1002/isaf.70011","DOIUrl":"https://doi.org/10.1002/isaf.70011","url":null,"abstract":"<p>The development of an in-house accounting bot—an artificial intelligence (AI) assistant capable of generating internally structured bookkeeping double-entry posting schemes—is explored in this paper. The processes of curating a suitable dataset, selecting, and fine-tuning a seven-billion-parameter language model, categorized as a small language model (SLM) (SLMs typically refer to models with fewer than 10 billion parameters, whereas medium-sized models often have 14B parameters, and large-scale models exceed 70B), are described. A human-evaluated benchmark is also presented to assess model performance. To achieve efficient supervised fine-tuning (SFT), low-rank adaptation (LoRA) was employed, significantly reducing memory requirements by using a small set of trainable parameters while maintaining model expressiveness. The process of backpropagation was further optimized using Unsloth, a high-performance training framework designed for efficient video memory usage and flash attention mechanisms, which accelerates adaptation and reduces memory overhead. The model whose layers were updated is called QwenCoder2.5. It was selected with the presumption that it would be able to learn how to generate and examine bookkeeping patterns generated by accounting information system (AIS) over a 17-year history. This proof of concept aims to support researchers and practitioners exploring the integration of generative AI in accounting by providing insights into both the benefits and challenges of AI-driven automation in bookkeeping tasks. The study demonstrates how an SLM can be fine-tuned on a proprietary dataset of journal posting schemes to assist accountants, auditors, and financial analysts while also facilitating synthetic data generation. Challenges related to AI, data preprocessing, fine-tuning optimization, and evaluation methodology are introduced and examined.</p>","PeriodicalId":53473,"journal":{"name":"Intelligent Systems in Accounting, Finance and Management","volume":"32 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/isaf.70011","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144716652","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}

{"title":"Social Media, Traditional News and Stock Returns: A Causal Mediation Analysis","authors":"Kingstone Nyakurukwa,&nbsp;Yudhvir Seetharam","doi":"10.1002/isaf.70012","DOIUrl":"https://doi.org/10.1002/isaf.70012","url":null,"abstract":"<p>Increasing computing power and access to the internet have amplified the role of social media and online news media on financial market outcomes. However, these two sources of information are intertwined in such a way that information flows between them. As a result, sentiment expressed in one source can affect stock market outcomes through the other source. This study examines this interplay between news media sentiment, social media sentiment and stock returns within the Dow Jones constituent companies from 2016 to 2023. Leveraging an extensive dataset, we adopt an approach that combines causal mediation models with robust statistical techniques to establish the mediation effects of one sentiment proxy on the relationship between the other proxy and stock returns. We also use a range of other methods like path analysis, panel vector autoregression and causal forests for robustness. The study finds that news sentiment is more influential in directly affecting stock returns than <i>Twitter</i> sentiment while the latter is more influential indirectly when mediated by news sentiment.</p>","PeriodicalId":53473,"journal":{"name":"Intelligent Systems in Accounting, Finance and Management","volume":"32 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/isaf.70012","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144647512","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}

{"title":"Editorial: Analysis of Sentiment Estimates and Cognitive Fallacies in Large Language Models","authors":"Daniel E. O'Leary","doi":"10.1002/isaf.70010","DOIUrl":"https://doi.org/10.1002/isaf.70010","url":null,"abstract":"<div>\u0000 \u0000 <p>This paper describes some experimentation with the evolving ability of large language models to generate sentiment estimates. We find that current models seem to equal or even exceed the ability of human annotators in a case study of single sentiment sentences. In addition, using the large language models, we were able to identify a small number of sentences in the data set, where it appears that the annotator made errors in assessing the sentiment. Unfortunately, analysis of the LLM results also illustrates apparent cognitive biases in the LLM behavior. Those effects appear to include an “ostrich effect” and a “no one is good enough” effect cognitive bias in LLM sentiment estimates.</p>\u0000 </div>","PeriodicalId":53473,"journal":{"name":"Intelligent Systems in Accounting, Finance and Management","volume":"32 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144624682","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}

{"title":"Comparing the Prediction Performance of Random Forest, Lasso, and Logit in the Context of IPO Withdrawal","authors":"Annika Reiff","doi":"10.1002/isaf.70009","DOIUrl":"https://doi.org/10.1002/isaf.70009","url":null,"abstract":"<p>This paper examines the prediction of IPO withdrawal using machine learning methods (lasso and random forest) and conventional regression (logit). The dataset comprises 2444 US first-time IPOs from 1997 to 2014. Results show that random forest outperforms both logit and lasso in in-sample and cross-sectional out-of-sample predictions when the training and test sets are drawn from the same time period. However, when models are trained on past data and tested on future observations, all models fail to accurately predict IPO withdrawal. This failure is attributed to concept drift—a change in the relationship between predictors and IPO withdrawal over time. I show that concept drift occurs at multiple points in time, affects various predictors, and persists even when accounting for economic shocks, institutional changes, or different prediction horizons. These findings suggest that the generalizability of previous results on IPO withdrawal is limited, as the relationship between various predictors and IPO withdrawal seems to vary across time periods.</p>","PeriodicalId":53473,"journal":{"name":"Intelligent Systems in Accounting, Finance and Management","volume":"32 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/isaf.70009","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144573470","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}