Machine learning and economics: bibliometric analysis

The purpose of the study, is to examine the development of international studies on machine learning in the field of economics and econometrics using Bibliometric Analysis and to visualize by Social Network Analysis between 2010 and 2019 in the Web of Science database. Methodology-Bibliometric Analysis is used to gather information about a discipline and to measure scientific productivity and progress. Social network analysis shows the relationship structure by visualizing the findings obtained as a result of bibliometric analysis. Findings-As a result of the bibliometric analysis, findings were obtained on the basis of variables such as the changes in the studies on the basis of years, the most published authors and the most cited studies, the distribution of these studies by countries and institutions, the course of the study topic, and the progress in the relational formation in the keywords. In addition, with the Social Network Analysis, the authors that network with each other and clusters and relationships between countries and keywords were mapped. Conclusion-When the findings were examined, it was determined that the most studies on these topics were conducted in the United States of America in each year and the most cited study was Varian (2014). At the same time, when the studies are evaluated in the last decade, it has been observed that the tendency towards the subjects of Machine learning, which attracts attention in Economics and Econometrics, has increased rapidly. It has been observed that the studies are associated with the keywords "causality" and "causal effect" as well as "Financial Econometrics", "Behavioral Economics", "Experimental Economics". The findings obtained shed light on the development of Machine Learning in the fields of Economics and Econometrics.