Background: Transitions from a linear (take-make-dispose) to a circular product system (consideringreuse/remanufacturing/recycling) require changes of business models through new value propositions.Therefore, the focus for industrial businesses shifts from selling physical products to, for example,providing access to functionality through business innovation. In this context it is particularly challengingto understand what complexity a new concept like circular economy (CE) brings to establishedbusinesses where the success and the failure of the business is dependent on customer’s acceptance ofnew value propositions.Objective: The objective of this paper is to develop an algorithm based on gathered survey data to “learn”choice behavior of a small customer group and then replicate that choice behavior on a larger populationlevel.Purpose: This paper explores the opportunities of different circular business offers in the city of Stockholmby embedding support vector machine classifiers, which are trained on CE survey data, in asimulation model to quantify and study choice behavior on city level.Method: Stated choices from CE surveys including unique demographic data from the respondents, i.e.age, income, gender and education, are used for algorithm training. Based on the survey data, supportvector machine algorithms are trained to replicate the decision-making process of a small sample ofrespondents. The example of a washing machine is used as a case study with the attributes price andpayment scheme, environmental friendliness as well as service level. The trained support vector machinesare then implemented in a simulation model to simulate choice behavior on population level(Stockholm city).Originality: This paper is the first of its kind to use both machine learning and simulation approaches in aCE market acceptance context.Findings: Based on the washing machine-specific survey and Stockholm-specific customer data, resultsindicate that larger share of the Stockholm population would be willing to opt for circular washingmachine offers compared to the existing linear sales model. Given the data-driven nature of machinelearning algorithms and the process-oriented structure of simulations programs allows for generatinglarge amounts of data from small samples. This supports exploration of new emerging areas like CE inaddition to saving time and expenses.