Lismont, JasmienVan Calster, TineÓskarsdóttir, Maríavanden Broucke, SeppeBaesens, BartLemahieu, WilfriedVanthienen, Jan2019-12-132019-12-1320192019http://dx.doi.org/10.1007/s12599-018-0539-zhttps://dl.gi.de/handle/20.500.12116/30645Generating insights and value from data has become an important asset for organizations. At the same time, the need for experts in analytics is increasing and the number of analytics applications is growing. Recently, a new trend has emerged, i.e. analytics-as-a-service platforms, that makes it easier to apply analytics both for novice and expert users. In this study, the authors approach these new services by conducting a full-factorial experiment where both inexperienced and experienced users take on an analytics task with an analytics-as-a-service technology. The research proves that although experts in analytics still significantly outperform novices, these web-based platforms do offer an advantage to inexperienced users. Furthermore, the authors find that analytics-as-a-service does not offer the same benefits across different analytics tasks. That is, they observe better performance for supervised analytics tasks. Moreover, this study indicates that there are significant differences between novices. The most important distinction lies in the approach they take on the task. Novices who follow a more complex, although structured, workflow behave more similarly to experts and, thus, also perform better. The findings can aid managers in their hiring and training strategy with regards to both business users and data scientists. Moreover, it can guide managers in the development of an enterprise-wide analytics culture. Finally, the results can inform vendors about the design and development of these platforms.Analytics-as-a-serviceAutomated analyticsData analyticsExperimental studyNovicesText/Journal Article10.1007/s12599-018-0539-z1867-0202