Special issue on machine learning and artificial intelligence in business and economics

Abstract

In academic studies, the integration of artificial intelligence (AI) and machine learning in the field of economics and finance has revolutionized research methodologies and enhanced the understanding of complex economic phenomena. Researchers can now analyze vast amounts of data more efficiently, identify patterns and trends, and develop predictive models with greater accuracy. This enables academics to delve deeper into economic theories, test hypotheses, and make more informed policy recommendations. Furthermore, the use of AI and machine learning algorithms in academic studies can lead to new insights, innovative research approaches, and interdisciplinary collaborations.

The leading article of this special issue, “Finance research over 40 years: What can we learn from machine learning?”, investigated on the topic distributional features of the research in finance over the past 40 years. This is the most thorough investigation on such a large field about the research topics, authorship distributions, using the method of machine learning. The authors have conducted a study applying machine learning models to analyze a data set comprising 20,185 finance articles published across 17 finance journals from 1976 to 2015. Through this analysis, they have objectively identified 38 research topics within the field. Among these topics, the financial crisis, hedge/mutual fund, social network, and culture emerged as the fastest-growing areas, while market microstructure, initial public offering, and option pricing experienced a decline in interest from 2006 to 2015. The authors also find a very interesting exponential decay rule for the number of topics that authors are covering.

A similar paper “Topic modeling of financial accounting research over 70 years” investigated topic distributions and time series patterns in financial accounting research in the past 70 years using machine learning methods. The author finds that The topics of mergers and acquisitions, disclosure and internal control, and political connection exhibited the most rapid expansion, whereas management control systems, earnings management, and valuation experienced the greatest contraction from 2014 to 2023. This research on topic classification itself will aid accounting investigators in bypassing superfluous efforts and fostering increased interdisciplinary research.

Beyond the topic modeling, there are two papers in this special issue regarding using machine learning in asset pricing. The paper “Investigating the profit performance of quantitative timing trading strategies in the Shanghai copper futures market, 2020–2022” investigates the time series signals using machine learning methods in the Shanghai copper futures market. The authors prudently conduct a reality check and advanced assessments to avoid data snooping problem. The basic conclusion of the paper demonstrates that after eliminating the data snooping bias, the time series signal within the class of investigation in the futures market are difficult to generate consistent profits.

The paper “Factor timing in the Chinese stock market” conducts an exploratory study about the feasibility of factor timing in the Chinese stock market, covering 24 representative and well-identified risk factors in 10 categories from the literature. The long–short portfolio of short-term reversal exhibits strong out-of-sample predictability, which is robust across various models and all types of predictors. Unlike the previous paper, this paper demonstrates significant predictability of prediction power in the time series of factors portfolio in Chinese stock market.

In the end, the special issue includes two papers about using AI in economics and finance. The first one, “Palm as Decentralized Identifiers: Mitigate scrounging of platform economy,” raises a new economic model based on the KYC technology of AI Palm recognition. The technology has the potential of addressing or reducing the scrounging problem in the platform economy, leading to increased efficiency of platform promotions. The second paper “A new era of financial services: How AI enhances investment efficiency” gives a nice summary of the AI technologies that are adopted in the Eastmoney.com, the largest digital financial investment platform in China.

From the above brief introduction, we can see that the papers in this special issue have contributed to our understanding of applying machine learning and AI in economics and finance. There are many more issues the papers of this special issue have not yet reached. We hope that the findings of these papers will encourage and inspire more interesting and fruitful studies in this field among our readers.

Ye Luo: conceptualization, formal analysis, writing–original draft, writing–review and editing.

The author has nothing to report.

The author declares no conflicts of interest.