As truly ubiquitous wearable computers, mobile phones are quickly becoming the primary source for social, behavioral, and environmental sensing and data collection. Today"s smartphones are equipped with increasingly more sensors and accessible data types that enable the collection of literally dozens of signals related to the phone, its user, and its environment. A great deal of research effort in academia and industry is put into mining this raw data for higher level sense-making, such as understanding user context, inferring social networks, learning individual features, predicting outcomes, and so on. In many cases, this analysis work is the result of exploratory forays and trial-anderror. Adding to the challenge, the devices themselves are a limited platform, and any data collection campaign must be carefully designed in order to collect the right signals, in the appropriate frequency, and at the same time not exhausting the device"s limited battery and processing power. There is need for a more structured methodology and tools to help with designing mobile data collection and analysis initiative.In this work we investigate the properties of learning and inference of real world data collected via mobile phones over time. In particular, we look at the dynamic learning process over time, and how the ability to predict individual parameters and social links is incrementally enhanced with the accumulation of additional data. To do this, we use the Friends and Family dataset, which contains rich data signals gathered from the smartphones of 140 adult members of a young-family residential community for over a year, and is one of the most comprehensive mobile phone datasets gathered in academia to date.We develop several models that predict social and individual properties from sensed mobile phone data, including detection of life-partners, ethnicity, and whether a person is a student or not. Then, for this set of diverse learning tasks, we investigate how the prediction accuracy evolves over time, as new data is collected. Finally, based on gained insights, we propose a method for advance prediction of the maximal learning accuracy possible for the learning task at hand, based on an initial set of measurements. This has practical implications, like informing the design of mobile data collection campaigns, or evaluating analysis strategies.