Development of Large-Scale Farming Based on Explainable Machine Learning for a Sustainable Rural Economy: The Case of Cyber Risk Analysis to Prevent Costly Data Breaches

Risk management is essential to every organization’s management plan. It is the strategy by which organizations handle the risks involved with their actions to profit or avoid making decisions that will cost them financially in each activity. Identifying and mitigating potential digital threats and developing and implementing procedures to significantly reduce the likelihood of an organization being targeted by cyberattacks are at the core of effective risk management. This is especially true regarding the risks associated with an organization’s digital footprint. A particularly significant threat to reputation, but also at the same time indirect and direct costs, is the data breach that occurs when a security incident occurs about the data for which the organization is responsible, which results in a violation of confidentiality, availability, or the integrity of the data it manages. On the other hand, the rapid development of technology has transformed the agricultural industry, allowing for large-scale farming based on machine learning and other advanced tools. However, this transformation also exposes farms to cyber risks that can lead to costly data breaches. In this study, we propose a framework for incorporating explainable machine learning (exML) techniques into large-scale farming to enhance cyber risk analysis, mitigate cyber threats, and foster a sustainable rural economy. Specifically, given that an organization needs to implement the appropriate technical and organizational measures to avoid possible data breaches, this work presents an analytical stochastic modeling of risk with a multi-criteria objective function of low complexity, a factor in an incentive system, to model investment value and cost balancing. The motivation behind the proposed method is to improve cybersecurity, protect data and reputation, foster a sustainable rural economy, leverage explainable machine learning, and adapt to the changing technological landscape. By addressing these motivations, the method aims to provide a comprehensive and effective approach to cyber risk analysis in large-scale farming.