Measuring timely high-resolution socioeconomic outcomes is critical for policymaking and evaluation, but hard to reliably obtain. With the help of machine learning and cheaply available data such as social media and nightlight, it is now possible to predict such indices in fine granularity. This article demonstrates an adaptive way to measure the time trend and spatial distribution of housing vitality (number of occupied houses) with the help of multiple easily accessible datasets: energy, nightlight, and land-use data. We first identified the high-frequency housing occupancy status from energy consumption data and then matched it with the monthly nightlight data. We then introduced the Factor-Augmented Regularized Model for prediction (FarmPredict) to deal with the dependence and collinearity issue among predictors by effectively lifting the prediction space, which is suitable to most machine learning algorithms. The heterogeneity issue in big data analysis is mitigated through the land-use data. FarmPredict allows us to extend the regional results to the city level, with a 76% out-of-sample explanation of the spatial and timeliness variation in the house usage. Since energy is indispensable for life, our method is highly transferable with the only requirement of publicly accessible data. Our article provides an alternative approach with statistical machine learning to predict socioeconomic outcomes without the reliance on existing census and survey data. Supplementary materials for this article are available online.

Biocultural approaches in anthropology originated from a desire to dissolve the nature/culture divide that is entrenched in the discipline. Whereas biocultural approaches were born under the umbrella of medical anthropology, by the late 1990s, biology-centered approaches to bioculturalism had been mostly taken up by human biologists in biological anthropology. It was at this point that biology-inclined approaches began to gel into an informal interdiscipline, biocultural anthropology. Much like any other discipline, biocultural anthropology developed research and professional norms with erected boundaries around acceptable work and workers. We draw from scholarly work in interdisciplinary studies to explore those norms and boundaries from the perspective of our collaborative, multimethod, and interdisciplinary project that combines “biology” and “culture” in unconventional ways. We provide examples of the obstacles, barriers, and risks we experienced and the costs exacted on the research project and the researchers due to the nature of our boundary crossings. By exploring biocultural anthropology from the edges of acceptability, we expose the unacknowledged boundary work in contemporary biocultural anthropology, and by extension, in its parent discipline, anthropology.