Differentiating Higher and Lower Job Performers in the Workplace Using Mobile Sensing

Abstract

Assessing performance in the workplace typically relies on subjective evaluations, such as, peer ratings, supervisor ratings and self assessments, which are manual, burdensome and potentially biased. We use objective mobile sensing data from phones, wearables and beacons to study workplace performance and offer new insights into behavioral patterns that distinguish higher and lower performers when considering roles in companies (i.e., supervisors and non-supervisors) and different types of companies (i.e., high tech and consultancy). We present initial results from an ongoing year-long study of N=554 information workers collected over a period ranging from 2-8.5 months. We train a gradient boosting classifier that can classify workers as higher or lower performers with AUROC of 0.83. Our work opens the way to new forms of passive objective assessment and feedback to workers to potentially provide week by week or quarter by quarter guidance in the workplace.

Understanding practices and needs of researchers in human state modeling by passive mobile sensing

“…2014 ; Mirjafari et al. 2019 )). Therefore, we focus on experienced researchers in this area who have a technical background.…”

“…2017 ), academic/work performance evaluation (Mirjafari et al. 2019 ; Wang et al. 2015 ), and routine modeling (Banovic et al.…”

How to Market Smart Products: Design and Pricing for Sharing Markets

“…Even more subtle is algorithmic tracking which has been in use on portable devices for at least a decade [24]. More recently, mobile sensing technologies have also been employed for consequential classification tasks such as the measurement of relative job performance [27]. Taken together, these developments can leave us with a sense of confidence that detecting usage transitions is a fairly easy task that can be accomplished on any reasonably enabled device.…”

“…To compute the solution to the firm's pricing problem in practice, one would usually start by determining the adjoint variable ψ r in Equation (25) [using the expression for � y 1 in Equation (21)], followed by η in Equation (27), σ in Equation (30), and σ in Equation (32), to be able to obtain the gradient g in Equation (37). Then, one would determine all candidates for the optimal marginal type θ � 0 based on the necessary optimality condition (38), to satisfy Equation (39).…”

“…The shape of this non-linear pricing curve is a simple and robust takeaway from our model. 27 One can interpret the flexible rent-extraction mechanism more broadly as an example of "servitization" [37], often viewed as a service add-on to hardware. 28 Indeed, given its user-sensing capability the company is adding on the service of authorizing sharing transactions by allowing transfers of its products between different users on a case-by-case basis, or in general.…”