Explains the working of “advantageous industries,” a new concept the authors define to explain why some industries are more valuable than others.

Artificial Intelligence Technologies (AITs) are already in large-scale use in two kinds of applications: consumer–product matching engines and user interfaces. AITs are core production technologies with hundreds of billions of dollars in revenue that involve no substitution of machine for human work at the task level; instead, there is capital deepening, not factor substitution, at the task level. The alternative – system-level substitution – is driven as much or more by output characteristics as by cost. With respect to long-run factor demand implications, there is no good reason to see AITs as different from other information and communication technologies (ICT) – they work at the system level to slowly change to a more capital-intensive, less labor-intensive, and more human-capital-intensive form of production and their early diffusion seems similar. Their largest impact is in a narrow range of industries and functions, notably consumer-oriented mass-market production, distribution, and marketing. Examining the strengths and weaknesses of AIT-based production illuminates both the narrowness and the depth of ICT application.

This chapter describes a process in which a number of long-standing hypotheses about sources of economic growth came to be represented as a series of modifications to Solow’s basic neoclassical production function, which in turn led to attempts to test empirically these hypotheses using production function regressions. Particular attention is given to two empirical research programs that made use of variants of Douglas’s regression procedure: the literature on “embodied technical change” initiated by Robert Solow, and Zvi Griliches’s work measuring the causes of economic growth, both of which emerged in the late 1950s and early 60s. Griliches and Solow proposed empirically tractable ways of testing various hypotheses about causes of economic growth. Their proposals were attractive in part because they made use of an empirical procedure, production function estimation, that involved statistical methods that were coming to be the foundation of graduate training in econometrics, and because they were expressed in terms of the mathematical neoclassical theory that was becoming central to graduate training in economic theory.