Cities are increasingly getting augmented with sensors through public, private, and academic sector initiatives. Most of the time, these sensors are deployed with a primary purpose (objective) in mind (e.g., deploy sensors to understand noise pollution) by a sensor owner (i.e., the organization that invests in sensing hardware, for example, a city council). Over the last few years, communities undertaking smart city development projects have understood the importance of making the sensor data available to a wider community – beyond their primary usage. Different business models have been proposed to achieve this, including creating data marketplaces. The vision is to encourage new start-ups and small and medium-scale businesses to create novel products and services using sensor data to generate additional economic value. Currently, data are sold as pre-defined independent datasets (e.g., noise level and parking status data may be sold separately). This approach creates several challenges, such as (i) difficulties in pricing, which leads to higher prices (per dataset), (ii) higher network communication and bandwidth requirements, and (iii) information overload for data consumers (i.e., those who purchase data). We investigate the benefit of semantic representation and its reasoning capabilities towards creating a business model that offers data on-demand within smart city Internet of Things (IoT) data marketplaces. The objective is to help data consumers (i.e., small and medium enterprises (SMEs)) acquire the most relevant data they need. We demonstrate the utility of our approach by integrating it into a real-world IoT data marketplace (developed by
synchronicity-iot.eu
project). We discuss design decisions and their consequences (i.e., trade-offs) on the choice and selection of datasets. Subsequently, we present a series of data modeling principles and recommendations for implementing IoT data marketplaces.