Jointly Predicting Job Performance, Personality, Cognitive Ability, Affect, and Well-Being

Assessment of individuals' job performance, personalized health and psychometric measures are domains where data-driven ubiquitous computing will have a profound impact in the near future. Existing work these focus on techniques that use data extracted from questionnaires, sensors (wearable, computer, etc.), or other traits to assess well-being cognitive attributes individuals. However, can neither predict psychological global manner nor consider challenges associated with processing often incomplete noisy available. In this paper, we create benchmark for predictive analysis individuals perspective integrates physical physiological behavior, states traits, performance. We develop novel mining framework extract meaningful predictors derived wearable, mobile social media nineteen constructs based twelve standardized well-validated tests. The be used build model outcomes interest. validate using 757 knowledge workers organizations across United States varied roles. Our resulting provides first combines various instrument-derived variables single understand people's behavior. results show our is reliable capable predicting chosen better than baselines when prediction includes data.