Can ChatGPT reduce human financial analysts' optimistic biases?

被引：7

作者：

Li, Xiaoyang ^{[1
]}

Feng, Haoming ^{[2
]}

Yang, Hailong ^{[2
]}

Huang, Jiyuan ^{[3
,4
,5
]}

机构：

[1] Hong Kong Polytech Univ, Sch Accounting & Finance, Hong Kong, Peoples R China

[2] Renmin Univ China, Sch Finance, Beijing, Peoples R China

[3] Univ Zurich, Dept Banking & Finance, Zurich, Switzerland

[4] Swiss Finance Inst, Zurich, Switzerland

[5] Univ Zurich, Swiss Finance Inst, Dept Banking & Finance, Zurich, Switzerland

来源：

ECONOMIC AND POLITICAL STUDIES-EPS | 2024年 / 12卷 / 01期

关键词：

ChatGPT; large language models; analyst forecast; optimistic biases; human-machine interaction; EARNINGS FORECASTS; INFORMATION; OWNERSHIP;

D O I：

10.1080/20954816.2023.2276965

中图分类号：

C [社会科学总论];

学科分类号：

03 ; 0303 ;

摘要：

This paper examines the potential of ChatGPT, a large language model, as a financial advisor for listed firm performance forecasts. We focus on the constituent stocks of the China Securities Index 300 and compare ChatGPT's forecasts for major financial performance measures with human analysts' forecasts and the realised values. Our findings suggest that ChatGPT can correct the optimistic biases of human analysts. This study contributes to the literature by exploring the potential of ChatGPT as a financial advisor and demonstrating its role in reducing human biases in financial decision-making.

引用

页码：20 / 33

页数：14

共 10 条

[1] The Influence of Cognitive Biases and Financial Factors on Forecast Accuracy of Analysts
Nardi, Paula Carolina Ciampaglia
Ribeiro, Evandro Marcos Saidel
Bueno, Jose Lino Oliveira
Aggarwal, Ishani
FRONTIERS IN PSYCHOLOGY, 2022, 12
[2] Can financial statement analysis beat consensus analysts' recommendations?
Wahlen, James M.
Wieland, Matthew M.
REVIEW OF ACCOUNTING STUDIES, 2011, 16 (01) : 89 - 115
[3] CAN YOU BELIEVE IT? MANAGERIAL DISCRETION AND FINANCIAL ANALYSTS' RESPONSES TO MANAGEMENT EARNINGS FORECASTS
Chen, Guoli
Crossland, Craig
FINANCE AND STRATEGY, 2014, 31 : 103 - 143
[4] How learning about behavioural biases can improve financial literacy?
Pitthan, Francisco
De Witte, Kristof
INTERNATIONAL REVIEW OF ECONOMICS & FINANCE, 2025, 99
[5] Can ChatGPT make reading comprehension testing items on par with human experts?
Shin, Dongkwang
Lee, Jang Ho
LANGUAGE LEARNING & TECHNOLOGY, 2023, 27 (03): : 27 - 40
[6] ChatGPT as a Commenter to the News: Can LLMs Generate Human-Like Opinions?
Tseng, Rayden
Verberne, Suzan
van der Putten, Peter
DISINFORMATION IN OPEN ONLINE MEDIA, MISDOOM 2023, 2023, 14397 : 160 - 174
[7] Human vs. AI: can ChatGPT improve tourism product descriptions?
Guttentag, Daniel A.
Litvin, Stephen W.
Teixeira, Rafael
CURRENT ISSUES IN TOURISM, 2024,
[8] Can Autograding of Student-Generated Questions Quality by ChatGPT Match Human Experts?
Li, Kangkang
Yang, Qian
Yang, Xianmin
IEEE TRANSACTIONS ON LEARNING TECHNOLOGIES, 2024, 17 : 1600 - 1610
[9] A knowledge curse: how knowledge can reduce human welfare
Basu, Kaushik
Weibull, Jorgen
ROYAL SOCIETY OPEN SCIENCE, 2024, 11 (08):
[10] Can Generative AI and ChatGPT Break Human Supremacy in Mathematics and Reshape Competence in Cognitive-Demanding Problem-Solving Tasks?
Kaya, Deniz
Yavuz, Selim
JOURNAL OF INTELLIGENCE, 2025, 13 (04)

← 1 →