Data, measurement, and causal inferences in machine learning: opportunities and challenges for marketing

ABSTRACT

The emergence of digital data and the methods used to analyze them are revolutionizing marketing research. The vast quantity of data offers marketing researchers countless opportunities to better predict and potentially explain consumer behavior. Yet, as we will argue in this paper, marketing researchers should not prematurely abandon cognitive and methodological procedures that have been refined during centuries of philosophical and scientific thought. Merging the literatures from various hard sciences, we discuss recent challenges in data management and measurement in the era of digital data and the role of machine learning in causal inference.

Notes

¹ Specifically, artificial intelligence is the broader concept of machines being able to carry out tasks in an intelligent manner, whereas machine learning is a practical field of artificial intelligence. That is, all machine learning counts as artificial intelligence, but not all artificial intelligence counts as machine learning. In the following, we primarily refer to machine learning methods.

² See Appendix A in Vermeer et al. (2019) for an overview of studies.

³ See https://www.youtube.com/watch?v=oAAo_r7ZT8U&feature=youtu.be for an example video.

Additional information

Funding

The authors received no financial support for the research, authorship, and/or publication of this article.