“…For instance, ML techniques have been widely applied to disease prognosis and prediction, such as predicting cancer susceptibility, recurrence and survival (e.g., Kourou, Exarchos, Exarchos, Karamouzis, & Fotiadis, 2015). Such predictive models can be transferred to an organizational setting where ML has been used to predict, for example, employee turnover (e.g., de Oliveira, Zylka, Gloor, & Joshi, 2019), return to work after sick leave (e.g., Na & Kim, 2019), physiological markers of stress (e.g., Bacciu, USING MACHINE LEARNING IN CAUSAL LEADERSHIP RESEARCH Colombo, Morelli, & Plans, 2018;Reddy, Thota, & Dharun, 2018), and employee performance (Kirimi, & Moturi, 2016). For leadership scholars who are interested in understanding relationships between leadership and follower, team, or organizational outcomes, the application of ML to data collected in the field represents an opportunity to examine exactly such relationships and build powerful leadership models.…”