In two months we finished reading “The Book of Why,” which gave us a glimpse into the fascinating world of causality. As ai-012315722793″ rel=”noopener”>fianceI have an extra article to close my first read with me series officially.
Inspired by my own experience as an academic researcher studying causal inference in economics during my Ph.D. program, as well as my experience as a data scientist in the industry building causal models to make demand forecasts, for the bonus article, I would like to share my understanding of the concept of causal inference and the similarities and differences in how it is applied. in academic and industrial environments.
Due to the difference in the nature and purpose of academic research and industrial applications, causal inference workflows are quite different between the two.
Speed
Academic research typically operates at a slower pace, from forming ideas to reaching final conclusions. It focuses on building confidence not only in the causal conclusion itself, but also in the data involved, the methods used, and the robustness of the research. Therefore, the research process is often extended to validate data eligibility, run sensitivity analyses, test causal structures, etc.
However, for business, time is money. technology companies are more practical. They prefer to focus their resources on creating scalable applications that can be put into production and generate profits quickly. The cost of waiting for a perfect and generalizable model is high. Therefore, the industry would prefer to have a reference model available as a placeholder before making adjustments and adjustments.
Method
In fact, academic research is a source of new approaches and mechanisms for theoretical researchers. However, empirical researchers who focus on observational studies or experiments tend to use standard, well-established methodologies. For example, differences in differences (DID)…