Association Rule Mining (ARM) is a data mining method intended for discovering relations between attributes in transaction databases in the form of implications (Agrawal & Srikant, 1994;. Traditional approaches, such as the Apriori algorithm (Agrawal & Srikant, 1994) or ECLAT (Zaki, 2000), require the attributes in the database to be discretized. This can result in the incorporation of noise into data, and potentially the obtained associations may not reveal the story fully (Varol Altay & Alatas, 2020). On the contrary, Numerical Association Rule Mining (NARM) is an extension of ARM that allows handling numerical attributes without discretization (Fister Jr. et al., 2021;Kaushik et al., 2020). Thus, an algorithm can operate directly, not only with categorical but also with numerical attributes concurrently. Interestingly, most NARM algorithms are based on stochastic population-based nature-inspired algorithms, which proved to be very efficient in searching for association rules (Alatas et al., 2008;Kaushik et al., 2021).