Activity based travel models are the main tools used to evaluate traffic conditions in the context of rapidly changing travel demand. However, data collection for activity based models is performed through travel surveys that are infrequent, expensive, and reflect the changes in transportation with significant delays. Thanks to the ubiquitous cell phone data, we see an opportunity to substantially complement these surveys with data extracted from network carrier mobile phone usage logs, such as call detail records (CDRs). Activity based travel demand models describe travel itineraries of individual users, namely (1) what activities users are participating in; (2) when users perform these activities; and (3) how users travel to the activity locales. In this paper, we first present a method of extracting user stay locations while not over-filtering short-term travel. Second, we apply Input-Output Hidden Markov Models (IO-HMMs) to reveal the activity patterns in real CDR data (with a focus on the San Francisco Bay Area regular commuters) collected by a major network carrier. No personally identifiable information (PII) was gathered or used in conducting this study. The mobility data that was analyzed was anonymous and aggregated in strict compliance with the carrier’s privacy policy. Our approach delivers actionable information to the practitioners in a form of a modular activity-based travel demand model, and captures the heterogeneous activity transition probabilities conditioned on spatial-temporal context.