Expectations Matter: When (Not) to Use Machine Learning Earnings Forecasts

References

• Baginski SP, Campbell JL, Ryu PW, Warren JD (2023) The association between current earnings surprises and the ex post bias of concurrently issued management forecasts. Rev. Accounting Stud. 28:2104–2149.Crossref, Google Scholar
• Ball RT, Ghysels E (2018) Automated earnings forecasts: Beat analysts or combine and conquer? Management Sci. 64:4936–4952.Link, Google Scholar
• Basu S (1997) The conservatism principle and the asymmetric timeliness of earnings. J. Accounting Econom. 24:3–37.Crossref, Google Scholar
• Bertomeu J (2020) Machine learning improves accounting: Discussion, implementation and research opportunities. Rev. Accounting Stud. 25:1135–1155.Crossref, Google Scholar
• Beyer A, Cohen DA, Lys TZ, Walther BR (2010) The financial reporting environment: Review of the recent literature. J. Accounting Econom. 50:296–343.Crossref, Google Scholar
• Boehmer E, Kelley EK (2009) Institutional investors and the informational efficiency of prices. Rev. Financial Stud. 22:3563–3594.Crossref, Google Scholar
• Bordalo P, Gennaioli N, Porta RL, Shleifer A (2019) Diagnostic expectations and stock returns. J. Finance 74:2839–2874.Crossref, Google Scholar
• Bradshaw MT (2011) Analysts’ forecasts: What do we know after decades of work? Preprint, submitted July 8, https://doi.org/10.2139/ssrn.1880339.Google Scholar
• Bradshaw MT, Richardson SA, Sloan RG (2001) Do analysts and auditors use information in accruals? J. Accounting Res. 39:45–74.Crossref, Google Scholar
• Bradshaw MT, Drake MS, Myers JN, Myers LA (2012) A re-examination of analysts’ superiority over time series forecasts of annual earnings. Rev. Accounting Stud. 17:944–968.Crossref, Google Scholar
• Breiman L (1996) Bagging predictors. Machine Learn. 24:123–140.Crossref, Google Scholar
• Brown LD, Call AC, Clement MB, Sharp NY (2015) Inside the “black box” of sell-side financial analysts. J. Accounting Res. 53:1–47.Crossref, Google Scholar
• Call AC, Hewitt M, Watkins J, Yohn TL (2021) Analysts’ annual earnings forecasts and changes to the I/B/E/S database. Rev. Accounting Stud. 26:1–36.Crossref, Google Scholar
• Cao K, You H (2024) Fundamental analysis via machine learning. Financial Analysts J. 80(2):74–98.Google Scholar
• Cao S, Jiang W, Wang J, Yang B (2024) From man vs. machine to man + machine: The art and AI of stock analyses. J. Financial Econom. 160:103910.Crossref, Google Scholar
• Chan LKC, Jegadeesh N, Lakonishok J (1996) Momentum strategies. J. Finance 51:1681–1713.Crossref, Google Scholar
• Chattopadhyay A, Fang B, Mohanram P (2025) Machine learning, earnings forecasting, and implied cost of capital: US and international evidence. Preprint, submitted December 20, https://doi.org/10.2139/ssrn.5941658.Google Scholar
• Chen X, Cho YHT, Dou Y, Lev B (2022) Predicting future earnings changes using machine learning and detailed financial data. J. Accounting Res. 60:467–515.Crossref, Google Scholar
• Chen P-C, Narayanamoorthy GS, Sougiannis T, Zhou H (2020) Analyst underreaction and the post-forecast revision drift. J. Bus. Finance Accounting 47:1151–1181.Crossref, Google Scholar
• De Bondt WFM, Thaler R (1990) Do security analysts overreact? Amer. Econom. Rev. 80:52–57.Google Scholar
• de Silva T, Thesmar D (2024) Noise in expectations: Evidence from analyst forecasts. Rev. Financial Stud. 37(5):1494–1537.Crossref, Google Scholar
• Dellavigna S, Pollet JM (2009) Investor inattention and Friday earnings announcements. J. Finance 64:709–749.Crossref, Google Scholar
• Easton PD, Kapons MM, Monahan SJ, Schutt HH, Weisbrod EH (2024) Forecasting earnings using k-nearest neighbors. Accounting Rev. 99:115–140.Crossref, Google Scholar
• Fama EF, MacBeth JD (1973) Risk, return, and equilibrium: Empirical tests. J. Political Econom. 81:607–636.Crossref, Google Scholar
• Frankel R, Lee CM (1998) Accounting valuation, market expectation, and cross-sectional stock returns. J. Accounting Econom. 25:283–319.Crossref, Google Scholar
• Friedman JH (2001) Greedy function approximation: A gradient boosting machine. Ann. Statist. 29(5):1189–1232.Crossref, Google Scholar
• Groysberg B, Healy PM, Maber DA (2011) What drives sell-side analyst compensation at high-status investment banks?: Analyst compensation at high-status banks. J. Accounting Res. 49:969–1000.Crossref, Google Scholar
• Hou K, Moskowitz TJ (2005) Market frictions, price delay, and the cross-section of expected returns. Rev. Financial Stud. 18:981–1020.Crossref, Google Scholar
• Hou K, van Dijk MA, Zhang Y (2012) The implied cost of capital: A new approach. J. Accounting Econom. 53:504–526.Crossref, Google Scholar
• Johnson TL, So EC (2018) Asymmetric trading costs prior to earnings announcements: Implications for price discovery and returns. J. Accounting Res. 56:217–263.Crossref, Google Scholar
• Lundberg SM, Erion GG, Lee S-I (2018) Consistent individualized feature attribution for tree ensembles. Preprint, submitted February 12, https://arxiv.org/abs/1802.03888.Google Scholar
• Newey WK, West KD (1987) A simple, positive semi-definite, heteroskedasticity and autocorrelation consistent covariance matrix. Econometrica 55:703.Crossref, Google Scholar
• Shapley L (1953) A value for n-person games. Kuhn HW, ed. Contributions to the Theory of Games, vol. II (Princeton University Press, Princeton, NJ), 307–317.Crossref, Google Scholar
• So EC (2013) A new approach to predicting analyst forecast errors: Do investors overweight analyst forecasts? J. Financial Econom. 108:615–640.Crossref, Google Scholar
• Uddin A, Tao X, Chou C-C, Yu D (2022) Are missing values important for earnings forecasts? A machine learning perspective. Quant. Finance 22:1113–1132.Crossref, Google Scholar
• van Binsbergen JH, Han X, Lopez-Lira A (2023) Man versus machine learning: The term structure of earnings expectations and conditional biases. Rev. Financial Stud. 36:2361–2396.Crossref, Google Scholar
• van Binsbergen JH, Han X, Lopez-Lira A (2025) Corrigendum: Man versus Machine Learning. Preprint, submitted January 22, https://doi.org/10.2139/ssrn.5037853.Google Scholar
• Zhang Y, Zhu Y, Linnainmaa JT (2024) Man versus machine learning revisited. Rev. Financial Stud. 38(12):3768–3790.Google Scholar