New Revolution in Fund Management: ETF/Index Design by Machines

Abstract

Two ETFs were listed to track the trends in the secondary-battery industry on September 12th, 2018 in the Korea Stock Exchange market. They are virtually identical except that one is designed by humans while the other is made by machines. This paper compares the two ETFs and find little difference in their investment strategies except that machines are more likely to pick high book-to-market stocks than humans. It also finds that machines are more likely to pick past losers than humans, and these stocks are shown to perform better afterwards, contributing to the outperformance of machine-designed ETF over humans. The results suggest that machines can do equally good as humans as ETF/index designers.

Keywords: ETF, index, machine learning

JEL Classification: D24, E22, E32, G12