Recommender systems can be used to assist groups of users to select services in Internet of Things (IoT)-enriched environments. However, aggregating the preferences of the individual users of a group, which is generally used in group recommendation, is not appropriate for IoT environments, where the user groups' preferences for IoT-based services differ significantly from those of individual users. In this paper, we propose a user-based collaborative filtering approach that considers member organization for a new user group. We select neighbor user groups that are similar to the new group based on combinations of member organization-based group similarity (MOGS) metrics such as the group size-based, common member-based, and member preference-based metrics. We conduct experiments to evaluate our approach using real-world datasets collected from practical IoT testbed environments. The results demonstrate that the proposed approach is effective in improving the performance and stability of service recommendations in IoT environments regardless of the locational characteristics.