Effectively modeling travel demand is essential for evaluating transportation policies, improving the transportation system and contributing to sustainable mobility. Traditionally, information about travel demand is gathered through travel surveys, questionnaires about an individual’s travel behavior during one or more days. This approach has seen dwindling response rates in recent years, along with high costs and associated biases. As an alternative, travel demand can be measured passively using mobile signaling data due to the proliferation and high penetration of mobile device usage. In this report, mobile signaling data processed by a third party and labeled with transportation mode using an eXtreme Gradient Boost Classifier trained through supervised learning using manually labeled data is evaluated as a potential replacement or complement to traditional travel surveying using questionnaires through a case study in Ale municipality, Sweden. The novel data source is validated quantitatively and qualitatively regarding the number of trips recorded, detected transportation mode, gender, age and time attributes. It is found that the number of trips is accurate in the mobile signaling data. And although the inferred transportation modes are found to be less accurate than the number of trips, information about modes is considered accurate enough for practical transportation planning purposes. Lastly, the gender attribute in the mobile signaling data most likely describes gender-differentiated travel better than the traditional travel survey, although this finding needs to be reaffirmed with further research, while the corresponding findings for the age attribute are inconclusive. As the evaluated data source offers an improved spatial and temporal resolution, novel use cases are made possible, such as evaluation of new infrastructure, more accurate predictions of travel demand and augmentation with census data to describe socio-demographic effects on travel behavior. More efforts should be put into producing an unsupervised mode inference model which would alleviate any quality problems associated with resource constraints in the data processing.