Search Results (52)

We investigate whether a belief in trend continuation, often associated with the so-called “hot-hand effect,” can be endogenously triggered by personal performance feedback in a controlled financial experiment. Participants allocated funds across assets with randomly generated prices, under conditions of known probabilities and varying levels of risk. In a two-stage setup, participants were first exposed to random price sequences to learn the task and potentially develop perceptions of personal success. They then faced additional price paths under incentivized conditions. Our findings show that participants initially increased purchases following gains—consistent with a feedback-driven belief in momentum—but this pattern faded over time. When facing sustained losses, loss aversion dominated decision-making, overriding early optimism. These results highlight how cognitive heuristics and emotional biases interact dynamically, suggesting that belief in trend continuation is context-sensitive and constrained by the reluctance to realize losses. Full article

This study examines how Environmental, Social, and Governance (ESG) reporting is communicated and perceived on YouTube. A dataset of 553 relevant videos and 5060 user comments was extracted on 2 April 2025 ranging between 2014 and 2025, and sentiment, topic, and stance analyses were applied to both transcripts and comments. The majority of video content strongly endorsed ESG reporting, emphasizing themes such as transparency, regulatory compliance, and financial performance. In contrast, viewer comments revealed diverse stances, including skepticism about methodological inconsistencies, accusations of greenwashing, and concerns over politicization. Notably, statistical analysis showed minimal correlation between video sentiment and audience sentiment, suggesting that user perceptions are shaped by factors beyond the tone of the videos themselves. These findings underscore the need for more rigorous ESG frameworks, enhanced standardization, and proactive stakeholder engagement strategies. The study highlights the value of online platforms for capturing stakeholder feedback in real time, offering practical insights for organizations and policymakers seeking to strengthen ESG disclosure and communication. Full article

This study investigates the yield-seeking behavior of income-oriented institutional investors, who are essential players in financial markets. While external pressures compelling firms to “reach for yield” are well-documented, the firm-level behavioral drivers underlying this phenomenon remain largely underexplored. Drawing on the behavioral theory of the firm, this study argues that an investor’s performance relative to their social aspiration level (the peer average) influences their yield-seeking decisions, and that this effect is moderated by “portfolio slack,” defined as unrealized gains or losses. To test this theory in the context of persistent low-yield pressure, this study constructs and analyzes a panel dataset of Japanese life insurance companies from 2000 to 2019. The analysis reveals that these investors increase their portfolio income yield after underperforming their peers and decrease it after outperforming. Furthermore, greater portfolio slack amplifies yield increases after underperformance and mitigates yield decreases after outperformance. In contrast, organizational slack primarily mitigates yield reductions after outperformance. This research extends the behavioral theory of the firm to the asset management context by identifying distinct performance feedback responses and proposing portfolio slack as an important analytical construct, thereby offering key insights for investment managers and financial regulators. Full article

Strategic financial decision-making is critical for organizational sustainability and competitive advantage. However, traditional approaches that rely solely on human expertise or isolated machine learning (ML) models often fall short in capturing the complex, multifaceted, and often asymmetrical nature of financial data, leading to suboptimal predictions and limited interpretability. This study addresses these challenges by developing an innovative, symmetry-aware integrated ML framework that synergizes decision trees, advanced ensemble techniques, and human expertise to enhance both predictive accuracy and model transparency. The proposed framework employs a symmetrical dual-feature selection process, combining automated methods based on decision trees with expert-guided selections, ensuring the inclusion of both statistically significant and domain-relevant features. Furthermore, the integration of human expertise facilitates rule-based adjustments and iterative feedback loops, refining model performance and aligning it with practical financial insights. Empirical evaluation shows a significant improvement in ROC-AUC by 2% and F1-score by 1.5% compared to baseline and advanced ML models alone. The inclusion of expert-driven rules, such as thresholds for debt-to-equity ratios and profitability margins, enables the model to account for real-world asymmetries that automated methods may overlook. Visualizations of the decision trees offer clear interpretability, providing decision-makers with symmetrical insight into how financial metrics influence bankruptcy predictions. This research demonstrates the effectiveness of combining machine learning with expert knowledge in bankruptcy prediction, offering a more robust, accurate, and interpretable decision-making tool. By incorporating both algorithmic precision and human reasoning, the study presents a balanced and symmetrical hybrid approach, bridging the gap between data-driven analytics and domain expertise. The findings underscore the potential of symmetry-driven integration of ML techniques and expert knowledge to enhance strategic financial decision-making. Full article

Return to play (RTP) decision making in professional soccer is crucial for minimising re-injury risk, reducing financial burdens on clubs, and optimising player performance. Despite its significance, there is a lack of objective criteria and consensus on RTP for adductor longus injuries, one of the most common muscle injuries in soccer. The aim of the present consensus was to validate an RTP protocol based on clinical, functional, and performance criteria through expert evaluation. This study hypothesises that a validated RTP protocol for adductor longus injuries will enhance decision making, reduce re-injury rates, and improve player performance upon return. An observational survey was designed to validate an RTP protocol through an expert panel. A total of 63 injury-management professionals (strength and conditioning coaches, physiotherapists, doctors, and rehabilitation fitness coaches) with an average experience of 12.02 ± 6.87 years participated in validating a 20-criteria RTP protocol. The protocol, divided into clinical, functional, and performance criteria, was assessed using a 5-point Likert scale. Aiken’s V coefficient was calculated for content validity, with criteria validated if Aiken’s V ≥ 0.75. Out of 20 initial RTP criteria, 14 were validated by the expert panel, with Aiken’s V ranging from 0.77 to 0.94 (overall range: 0.61–0.98). Key validated criteria included pain on palpation, flexibility, imaging, athlete feedback, strength assessments, movement quality, pre-injury GPS data, and performance under simulated match conditions. Criteria such as the Copenhagen adduction exercise and specific agility tests were not validated. The expert-validated RTP protocol for adductor longus injuries provides a structured approach to decision making, potentially reducing re-injury risk, improving rehabilitation strategies, and enhancing player performance. These findings could be integrated into clinical sports-medicine practices to enhance rehabilitation effectiveness and RTP decisions in professional soccer. Full article

Effective investment decision-making in today’s volatile financial market demands the integration of advanced predictive analytics, alternative data sources, and behavioral insights. This paper introduces an innovative Internet of Behaviors (IoB) ecosystem that integrates real-time data acquisition, advanced feature engineering, predictive modeling, explainability, automated portfolio management, and an intelligent decision support engine to enhance financial decision-making. Our framework effectively captures complex temporal dependencies in financial data by combining robust technical indicators and sentiment-driven metrics—derived from BERT-based sentiment analysis—with a multi-layer LSTM forecasting model. To enhance the model’s performance and transparency and foster user trust, we apply XAI methods, namely, TimeSHAP and TIME. The IoB ecosystem also proposes a portfolio management engine that translates the predictions into actionable strategies and a continuous feedback loop, enabling the system to adapt and refine its strategy in real time. Empirical evaluations demonstrate the effectiveness of our approach: the LSTM forecasting model achieved an RMSE of 0.0312, an MAE of 0.0250, an MSE of 0.0010, and a directional accuracy of 95.24% on TSLA stock returns. Furthermore, the portfolio management algorithm successfully transformed an initial balance of USD 15,000 into a final portfolio value of USD 21,824.12, yielding a net profit of USD 6824.12. These results highlight the potential of IoB-driven methodologies to revolutionize financial services by enabling more personalized, transparent, and adaptive investment solutions. Full article

Customers are the cornerstone of business success across industries. Companies invest significant resources in acquiring new customers and, more importantly, retaining existing ones. However, customer churn remains a major challenge, leading to substantial financial losses. Addressing this issue requires a deep understanding of customers’ cognitive status and behaviours, as well as early signs of churn. Predictive and Machine Learning (ML)-based analysis, when trained with appropriate features indicative of customer behaviour and cognitive status, can be highly effective in mitigating churn. A robust ML-driven churn analysis depends on a well-developed feature engineering process. Traditional churn analysis studies have primarily relied on demographic, product usage, and revenue-based features, overlooking the valuable insights embedded in customer–company interactions. Recognizing the importance of domain knowledge and human expertise in feature engineering and building on our previous work, we propose the Customer Churn-related Knowledge Base (ChurnKB) to enhance feature engineering for churn prediction. ChurnKB utilizes textual data mining techniques such as Term Frequency-Inverse Document Frequency (TF-IDF), cosine similarity, regular expressions, word tokenization, and stemming to identify churn-related features within customer-generated content, including emails. To further enrich the structure of ChurnKB, we integrate Generative AI, specifically large language models, which offer flexibility in handling unstructured text and uncovering latent features, to identify and refine features related to customer cognitive status, emotions, and behaviours. Additionally, feedback loops are incorporated to validate and enhance the effectiveness of ChurnKB.Integrating knowledge-based features into machine learning models (e.g., Random Forest, Logistic Regression, Multilayer Perceptron, and XGBoost) improves predictive performance of ML models compared to the baseline, with XGBoost’s F1 score increasing from 0.5752 to 0.7891. Beyond churn prediction, this approach potentially supports applications like personalized marketing, cyberbullying detection, hate speech identification, and mental health monitoring, demonstrating its broader impact on business intelligence and online safety. Full article

The automotive industry, especially the after-sales service segment, faces significant challenges due to economic changes and market dynamics. In this context, the optimization of service processes becomes essential to increase the performance and profitability of organizations in the industry. However, there is a lack of research that specifically and in detail explores how to model service processes to improve performance in this sector. Most studies focus on general aspects of quality management or process optimization without addressing the particularities of after-sales services in the automotive industry. This paper aims to identify and analyze how to model service processes in an automotive repair service provider organization to increase performance and ensure customer satisfaction. This research was conducted using data from service activity reports and participatory direct observation within an automotive repair service provider organization. Statistical analysis of key performance indicators, such as productivity, efficiency, and customer satisfaction, was performed. This study identified several critical success factors and proposed concrete measures for shaping service processes, including optimizing resource allocation and customer communication, improving customer intake and communication, ensuring technical competence and procedural compliance, and improving the process of handing over and collecting feedback. The implementation of these measures can lead to increased efficiency, customer satisfaction, and, by extension, the financial performance of automotive repair organizations. Full article

This study investigates the interplay between budget planning and budgeting evaluation functions in relation to company budget management performance, specifically focusing on the phenomenon of budgetary slack among manufacturing companies in China. A total of 589 employees, including senior executives and finance managers, participated in this study to answer structured questionnaires. Structural Equation Modeling (SEM) was used to test the proposed research hypotheses; furthermore, Hayes’ mediation analysis was applied to assess the direct and indirect effects of budgetary slack in mediating the relationship between the predictor variable (e.g., budget planning and budgeting evaluation) and the outcome variable (budgeting performance). The findings reveal that both budget planning and evaluation significantly mitigate budgetary slack while enhancing the overall budget management performance. The results suggest that effective budgeting performance is positively influenced by the quality of budget planning and evaluation functions, which directly and indirectly reduce budgetary slack. Such evidence underscores the critical role of the budgeting management process in achieving optimal budgeting performance, with budgeting evaluation serving as a catalyst for constructive feedback to prevent slack. This study advocates for companies to strengthen the alignment between their budgeting processes and budgeting strategies. Furthermore, this research provides a comprehensive strategy that integrates technology, strategic budget management, and financial governance, equipping business entities to navigate and thrive in a dynamic economic landscape. Full article

How do CEOs’ unique early-life experiences—particularly those shaped by formative influences such as military training—impact their subsequent strategic decision-making in green innovation? By integrating upper-echelon theory, imprinting theory, and the green innovation literature, this paper explores whether and when a CEO’s military background influences a firm’s adoption of green innovation practices, specifically within an emerging market context. Analyzing a sample of 1419 Chinese listed firms over the period from 2007 to 2016, our results reveal a significant positive effect of a CEO’s military experience on the firm’s green innovation performance. Furthermore, we find that a firm’s positive financial performance amplifies the influence of the CEO’s military imprint on green innovation outcomes. However, the intensity of government environmental regulation moderates this effect, weakening the relationship between the CEO’s personal values and the firm’s green innovation performance. Theoretical and practical implications are discussed. Full article

Accurate disclosure and proactive engagement in ESG practices are essential for achieving high-quality economic development, particularly as China addresses significant challenges during its reform journey. The Classified Reform of State-Owned Enterprises (CRSOE) is a strategic initiative by the Chinese government aimed at fostering this development. Our study leverages the implementation of the CRSOE as an exogenous shock, employing the difference-in-differences approach to assess the policy’s governance impact on ESG decoupling from the perspective of ownership heterogeneity. The policy was found to alleviate ESG decoupling, particularly pronounced among SOEs with special functions. The governance effect is achieved by reducing the aspiration–performance gap. Specifically, the policy effectively narrows the disparity between a company’s actual performance and the expected performance based on the industry average, thereby mitigating ESG decoupling. However, the policy’s impact can be weakened by factors such as political connections among executives and media attention. Furthermore, the CRSOE effectively addresses greenwashing practices within ESG decoupling, with a particularly strong effect on SOEs that fail to disclose ESG information in alignment with Global Reporting Initiative (GRI) standards. These findings highlight the importance of understanding the broader implications and underlying mechanisms of the policy. Therefore, building on the assessment of how the CRSOE policy impacts ESG decoupling, we also examine the mechanisms through which this policy operates and how its effectiveness varies under different conditions of heterogeneity. By extending the application of principal-agent theory and performance feedback theory, our research suggests that policymakers should prioritize market-driven reforms for fully competitive SOEs and promote a stronger emphasis on non-financial goals. Additionally, it is essential to mitigate the undue influence of political promotions on the management of all SOEs. Full article

Building maintenance and operation costs represent a significant portion of the life cycle costs (LCC) of construction projects. The accurate estimation of these costs is essential for ensuring the long-term sustainability and financial efficiency of buildings. This study aims to develop a novel framework for predicting maintenance and operation costs in construction projects by integrating an emotional artificial neural network (EANN). Unlike traditional models that rely on linear regression or static machine learning, the EANN dynamically adapts its learning through synthetic emotional feedback mechanisms and advanced optimization techniques. The research collected input data from 313 experts in the field of building management and construction in Ha’il, Saudi Arabia, through a comprehensive questionnaire. The integration of expert opinions with advanced machine learning techniques contributes to the innovative approach, providing more reliable and adaptive cost predictions. The proposed EANN model was then compared with a classic artificial neural network (ANN) model to evaluate its performance. The results indicate that the EANN model achieved an R² value of 0.85 in training and 0.81 in testing for buildings aged 0 to 10 years, significantly outperforming the ANN model, which achieved R² values of 0.78 and 0.72, respectively. Additionally, the Root Mean Squared Error (RMSE) for the EANN model was 1.57 in training and 1.60 in testing, lower than the ANN’s RMSE values of 1.82 and 1.90. These findings show that the superior capability of the EANN model in estimating maintenance and operation costs.. This led to more accurate long-term maintenance cost projections, reduced budgeting uncertainty, and enhanced decision-making reliability for building managers. Full article

Sentiment analysis is a well-known task that has been used to analyse customer feedback reviews and media headlines to detect the sentimental personality or polarisation of a given text. With the growth of social media and other online platforms, like Twitter (now branded as X), Facebook, blogs, and others, it has been used in the investment community to monitor customer feedback, reviews, and news headlines about financial institutions’ products and services to ensure business success and prioritise aspects of customer relationship management. Supervised learning algorithms have been popularly employed for this task, but the performance of these models has been compromised due to the brevity of the content and the presence of idiomatic expressions, sound imitations, and abbreviations. Additionally, the pre-training of a larger language model (PTLM) struggles to capture bidirectional contextual knowledge learnt through word dependency because the sentence-level representation fails to take broad features into account. We develop a novel structure called language feature extraction and adaptation for reviews (LFEAR), an advanced natural language model that amalgamates retrieval-augmented generation (RAG) with a conversation format for an auto-regressive fine-tuning model (ARFT). This helps to overcome the limitations of lexicon-based tools and the reliance on pre-defined sentiment lexicons, which may not fully capture the range of sentiments in natural language and address questions on various topics and tasks. LFEAR is fine-tuned on Hellopeter reviews that incorporate industry-specific contextual information retrieval to show resilience and flexibility for various tasks, including analysing sentiments in reviews of restaurants, movies, politics, and financial products. The proposed model achieved an average precision score of 98.45%, answer correctness of 93.85%, and context precision of 97.69% based on Retrieval-Augmented Generation Assessment (RAGAS) metrics. The LFEAR model is effective in conducting sentiment analysis across various domains due to its adaptability and scalable inference mechanism. It considers unique language characteristics and patterns in specific domains to ensure accurate sentiment annotation. This is particularly beneficial for individuals in the financial sector, such as investors and institutions, including those listed on the Johannesburg Stock Exchange (JSE), which is the primary stock exchange in South Africa and plays a significant role in the country’s financial market. Future initiatives will focus on incorporating a wider range of data sources and improving the system’s ability to express nuanced sentiments effectively, enhancing its usefulness in diverse real-world scenarios. Full article

The effects of greenwashing as a corporate strategy on firm risk are not well defined. I construct a greenwashing measure for 3973 companies from 70 countries from 2012 to 2022. Using Dynamic Panel Modeling, I find results suggesting that greenwashing is a complex phenomenon with both positive and negative consequences. While it can improve a firm’s public image and potentially enhance its financial performance, it may also lead to increased risk and misallocation of resources. Greenwashing firms have a lower weighted average cost of capital due to a higher debt-to-capital ratio. They are larger, have higher institutional ownership, and lower dividend yields. On the other hand, greenwashing firms have more ESG-related controversies that can hurt firm revenues and market value, they have higher unsystematic risk, and they have lower dividend yields and return on equity. I also find evidence that there is a feedback relationship between ESG ratings and greenwashing. There is no evidence that government mandates on ESG reporting inhibit greenwashing. The implication is that ESG scoring that emphasizes reporting ESG activities while informing investors also encourages greenwashing. Full article

Climate change, through more frequent extreme weather events, and urban sprawl, by increasing runoff, are two critical threats to drainage networks, impacting both public health and property. Augmenting drainage networks to withstand additional stress by enlarging conduits or constructing new detention facilities requires a significant financial investment. The goal of this study is to enhance urban resilience by optimizing real-time control (RTC) systems for drainage networks that optimize the flow control devices (FCDs), which could mitigate the need to invest in major construction costs. RTC is an approach that can help mitigate flooding in urban areas. This study is the first to optimize feedback controllers in SWMM, as well as the first to simultaneously optimize the number, location, and proportional–integral–derivative (PID) controllers for FCDs through two nested genetic algorithms (GAs), and especially within a unified environment (i.e., Python), which led to more efficient management of the process, thereby enhancing the efficiency of urban drainage network optimization. This study examined the impact of optimized RTC on the urban drainage network (UDN) in a part of New Orleans, LA, USA, under 1-, 2-, 5-, and 10-year storm events. The optimized RTC resulted in an improvement of up to 50% in network performance during a design storm. The results demonstrate the applicability in an urban environment where storms, flooding, and financial investments are critical to the management of stormwater drainage. Full article