2021
DOI: 10.2139/ssrn.3840538
|View full text |Cite
|
Sign up to set email alerts
|

From Man vs. Machine to Man + Machine: The Art and AI of Stock Analyses

Abstract: An AI analyst we build to digest corporate financial information, qualitative disclosure, and macroeconomic indicators is able to beat the majority of human analysts in stock price forecasts and generate excess returns compared to following human analysts. In the contest of "man vs machine," the relative advantage of the AI Analyst is stronger when the firm is complex, and when information is high-dimensional, transparent and voluminous. Human analysts remain competitive when critical information requires inst… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
7
0
2

Year Published

2022
2022
2024
2024

Publication Types

Select...
7

Relationship

0
7

Authors

Journals

citations
Cited by 10 publications
(9 citation statements)
references
References 112 publications
0
7
0
2
Order By: Relevance
“…Thus, while some tasks are clearly at risk of substitution by digital tools (especially simple and repeated tasks), many other tasks are unlikely to be fully completed using digital tools (Acemoglu, Autor, Hazell, & Restrepo, 2020). For example, Cao, Jiang, Wang, and Yang (2021) built an AI analyst to analyze financial information for investment decisions. The authors find that people and tools have complementary capabilities: Humans outperform AI when contextual information matters while AI outperforms people when the information is voluminous, transparent, and high‐dimensional.…”
Section: Digital Transformationmentioning
confidence: 99%
See 1 more Smart Citation
“…Thus, while some tasks are clearly at risk of substitution by digital tools (especially simple and repeated tasks), many other tasks are unlikely to be fully completed using digital tools (Acemoglu, Autor, Hazell, & Restrepo, 2020). For example, Cao, Jiang, Wang, and Yang (2021) built an AI analyst to analyze financial information for investment decisions. The authors find that people and tools have complementary capabilities: Humans outperform AI when contextual information matters while AI outperforms people when the information is voluminous, transparent, and high‐dimensional.…”
Section: Digital Transformationmentioning
confidence: 99%
“…Yet this initial AI advantage declined over time as humans were able to absorb more information. The authors predict that ultimately digital tools like AI for high‐skill professionals will be complements to people rather than substitutes (Cao et al, 2021). Similarly, Agrawal et al (2018) argue that a combination of digital tools and people has the highest success rate in ambiguous, novel, or holistic settings like cancer detection.…”
Section: Digital Transformationmentioning
confidence: 99%
“…5 GBMs have been used in finance research on return prediction, director turnover prediction and stock valuation (e.g., Gu, Kelly, and Xiu [2020], Erel et al [2021], Cao et al [2021]). Section A.2 in the appendix provides an in-depth explanation of GBMs.…”
Section: Gradient Boosting Machinesmentioning
confidence: 99%
“…Os autores preveem que, em última análise, ferramentas digitais como IA para profissionais de alta habilidade serão complementos para as pessoas e não substitutos (Cao et al, 2021). Da mesma forma, Agrawal et al (2018) argumentam que uma combinação de ferramentas digitais e pessoas tem a maior taxa de sucesso em ambientes ambíguos, novos ou holísticos, como a detecção de câncer.…”
Section: 3| Tensão 3: Pessoas Vs Ferramentasunclassified