A Two-Stage Algorithm for Cost-Efficient Multi-instance Counterfactual Explanations

Counterfactual explanations constitute among the most popular methods for analyzing the predictions of black-box systems since they can recommend cost-efficient and actionable changes to the input to turn an undesired system's output into a desired output. While most of the existing counterfactual methods explain a single instance, several real-world use cases, such as customer satisfaction, require the identification of a single counterfactual that can satisfy multiple instances (e.g. customers) simultaneously. In this work, we propose a flexible two-stage algorithm for finding groups of instances along with cost-efficient multi-instance counterfactual explanations. This is motivated by the fact that in most previous works the aspect of finding such groups is not addressed.

V2X communication coverage analysis for connected vehicles in intelligent transportation networks: A case study for the city of Xanthi, Greece

Intelligent transportation systems (ITS) have been developed to improve traffic flow, efficiency, and safety in transportation. Technological advancements in communication such as the Vehicle-to-Everything (V2X), Vehicle-to-Vehicle (V2V) and Vehicle-to Infrastructure (V2I) enable the real-time exchange of information between vehicles and other entities on the road network, and thus play a significant role in their safety and efficiency. This paper presents a simulation study that models V2V and V2I communication to identify the most suitable range of data transmission between vehicles and infrastructure. The provincial city of Xanthi, Greece is used as a cases study, and the goal is to evaluate whether the proposed placement of Road Side Unit (RSU) provided adequate communication coverage on the city's road network. An analysis through different scenarios identified improvements in traffic management, driving behavior and environmental conditions under different RSU coverage. The results highlight that the communication range of 400 meters is the most adequate option for optimum traffic management in the city of Xanthi.

"How to make them stay?" -- Diverse Counterfactual Explanations of Employee Attrition

Employee attrition is an important and complex problem that can directly affect an organisation's competitiveness and performance. Explaining the reasons why employees leave an organisation is a key human resource management challenge due to the high costs and time required to attract and keep talented employees. Businesses therefore aim to increase employee retention rates to minimise their costs and maximise their performance. Machine learning (ML) has been applied in various aspects of human resource management including attrition prediction to provide businesses with insights on proactive measures on how to prevent talented employees from quitting. Among these ML methods, the best performance has been reported by ensemble or deep neural networks, which by nature constitute black box techniques and thus cannot be easily interpreted. To enable the understanding of these models' reasoning several explainability frameworks have been proposed. Counterfactual explanation methods have attracted considerable attention in recent years since they can be used to explain and recommend actions to be performed to obtain the desired outcome. However current counterfactual explanations methods focus on optimising the changes to be made on individual cases to achieve the desired outcome. In the attrition problem it is important to be able to foresee what would be the effect of an organisation's action to a group of employees where the goal is to prevent them from leaving the company. Therefore, in this paper we propose the use of counterfactual explanations focusing on multiple attrition cases from historical data, to identify the optimum interventions that an organisation needs to make to its practices/policies to prevent or minimise attrition probability for these cases.