Alexander Maximilian Röser

The Neural Network Integrity Constraint (NNIC) approach is a novel technique that aims to improve the accuracy of neural network (NN) classifications by reducing misclassified instances using integrity constraints (ICs) derived from a held-out residual dataset (separate from the final test set). This ensures a leakage-free evaluation. The paper describes the NNIC approach and evaluates the effectiveness of the NNIC approach through six publicly available datasets. For each experiment, the dataset is split into different proportions of training and test data to assess the impact of varying data sizes on classification accuracy. The NNs are trained using the training data, and the misclassified instances from the residual data are identified. ICs are subsequently generated using the Random Forest Classifier (RFC) algorithm and applied at inference time to reduce classification errors. The number of test examples (only experiments with ICs) provides with 65,640 an intensive size for the evaluation of misclassified data. The results demonstrate that the NNIC approach significantly reduces misclassification rates across all six experiments, even with halved training data. The experiments record also the number of NN parameters as well as training and IC runtimes. These quantities are indicators of resource consumption but are not direct energy measurements. The NNIC approach relates also to Green AI since a significant reduction in computational effort and error rates is enabled.

This study investigates the impact of environmental, social, and governance (ESG) ratings on the systematic and unsystematic risk of European companies from 2017 to 2022. Using data from the STOXX Europe 600 Index, we employ panel regression and multiple linear regression analyses to examine two ESG rating methodologies: the Bloomberg Disclosure Score, which serves as a proxy for ESG transparency, and the Morningstar Sustainalytics Score, which represents ESG performance. To ensure robustness, control variables—including market capitalization, EBIT margin, debt-to-equity ratio, payout ratio, sector classification, and the risk-free interest rate—are included in the analyses. The main findings show that from 2017 to 2021, ESG transparency has a significant positive impact on systematic risk. In 2022, however, this relationship becomes negative, indicating a shift in the way transparency affects risk. Throughout the study period, no significant effect of ESG transparency on unsystematic risk is observed. Regarding ESG performance, the results show that in ESG-sensitive sectors, higher ESG performance significantly increases systematic risk from 2017 to 2019. From 2019 to 2022, better ESG performance is associated with a significant reduction in systematic risk. In addition, a significant positive impact on unsystematic risk is found from 2019 to 2022. These findings highlight the complex and dynamic relationship between ESG ratings and company risk profiles, which is influenced by factors such as time period, industry sensitivity, and rating methodology. The study underlines the importance of context in understanding the impact of ESG factors on investment risk.

This study investigates the impact of Environmental, Social, and Governance (ESG) scores on company value and market capitalization volatility in the German stock market. Using daily data from the DAX 40 index for the years 2022, 2023, and 2024, this study employs various regression models to analyze the relationship between ESG scores, market capitalization, and volatility. The results show that ESG scores have a positive influence on market capitalization in the initial pooled ordinary least squares (OLS) regression analysis, with the magnitude of the effect increasing over the three-year period. However, when controlling for company-specific characteristics using a fixed-effects regression, the influence of ESG scores on market capitalization becomes statistically insignificant. Conversely, this study finds a weak but statistically significant positive relationship between ESG scores and annual volatility, contradicting the common assumption that companies with higher ESG scores exhibit lower volatility. The analysis also reveals a size effect, with larger companies tending to have lower volatility. The study provides an up-to-date overview of the influence of sustainability on market capitalization and volatility, offering opportunities for further research by considering additional factors. These findings contribute to the ongoing debate on the financial implications of corporate sustainability practices and their impact on investor decision-making.