Abstract
Energy smart grids and other modern industrial control systems networks impose considerable security management challenges due to several factors: their broad geographic dispersion and capillarity, the constrained nature of many of the devices and network links that integrate them, and the fact that they are often fragmented across multiple domains, owned and managed by different entities which often have non-aligned or even competing interests. Due to this scenario, we propose to improve federated learning-based anomaly detection for smart grids and other industrial control networks, using a federated data-centric methodology that attends to the balance and causality of the data, improving the representation of the different classes of anomalies of the ingested data, which directly impact the classifier's performance. The proposed approach shows up to 33% performance improvements in terms of F1-score for attack classification, compared to the baseline federated approach (not attending to class imbalance and causality) on a broad range of industrial control systems traffic datasets.

Abstract

Abstract

Abstract
[No abstract available]

Abstract
The telecommunications sector faces a major challenge of high customer churn. Despite this, there is still a lack of research that explores the switching intention for telecommunication services, particularly with bundle services that currently dominate the market. This study aims to provide insight into consumer behaviour regarding bundle telecommunication services by examining the factors that impact satisfaction and switching intention, both directly and indirectly. Eighteen hypotheses were defined based on the literature, and were tested through a quantitative study with 910 bundle service customers using structural equation modelling with Smart-PLS. The results show that internet and television services have the strongest indirect impact on switching intention, mediated by overall satisfaction and loyalty. Additionally, the results indicate that switching costs and barriers do not significantly affect switching intention, and surprisingly, perceived contractual lock-in positively influences switching intention. This study provides a comprehensive understanding of the customer experience with bundled telecommunications services and offers relevant insights for telecommunication managers to prevent customer loss to competitors.

Abstract
This study aims to test the forecasting accuracy of recently implemented econometric tools as compared to the forecasting accuracy of widely used traditional models when predicting cash demand at ATMs. It also aims to verify whether the pandemic-driven change in market conditions impacted the predictive power of the tested models. Our conclusions were derived based on a data set that consisted of daily withdrawals from 61 ATMs of one of the largest European ATM networks operating in Krakow, Poland, and covered the period between January 2017 and April 2021. The results proved that the recently implemented methods of forecasting ATM withdrawals were more accurate as compared to the traditional ones, with XGBoost providing the best forecasts in the majority of the tested cases. Moreover, it was found that the pandemic-driven change in market conditions affected the predictive power of the models. Both of these results seem particularly useful for improving the efficiency of ATM networks.