This research essay by Galit Shmueli and O. Koppius highlights the importance of integrating predictive analytics into information systems (IS) research. Predictive analytics, which include empirical methods for generating data predictions and assessing predictive power, are crucial for creating practical models and enhancing theory building and testing. The authors identify six key roles for predictive analytics: new theory generation, measurement development, comparison of competing theories, improvement of existing models, relevance assessment, and assessment of the predictability of empirical phenomena. Despite their significance, predictive analytics are rare in empirical IS literature, which primarily relies on explanatory statistical modeling. The essay discusses the differences between explanatory and predictive modeling, emphasizing that explanatory power does not imply predictive power. It also presents methods for assessing predictive power and building predictive models, illustrated through a conversion of a well-known TAM study into a predictive context. The authors conclude by discussing the value of predictive analytics in scientific research and the need for their integration into IS research.This research essay by Galit Shmueli and O. Koppius highlights the importance of integrating predictive analytics into information systems (IS) research. Predictive analytics, which include empirical methods for generating data predictions and assessing predictive power, are crucial for creating practical models and enhancing theory building and testing. The authors identify six key roles for predictive analytics: new theory generation, measurement development, comparison of competing theories, improvement of existing models, relevance assessment, and assessment of the predictability of empirical phenomena. Despite their significance, predictive analytics are rare in empirical IS literature, which primarily relies on explanatory statistical modeling. The essay discusses the differences between explanatory and predictive modeling, emphasizing that explanatory power does not imply predictive power. It also presents methods for assessing predictive power and building predictive models, illustrated through a conversion of a well-known TAM study into a predictive context. The authors conclude by discussing the value of predictive analytics in scientific research and the need for their integration into IS research.