Forecasting Earnings Using k-Nearest Neighbor Matching

Easton, Peter D.; Kapons, Martin M.; Monahan, Steven J.; Schütt, Harm H.; Weisbrod, Eric H.

doi:10.2139/ssrn.3752238

Cited by 6 publications

(7 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Particularly, an algorithm to forecast annual earnings is of interest to any company. Such an algorithm has been proposed [62] that leverages k-NN. It matches a company's recent trend in annual earnings to historical earning sequences of other firms that are similar-known as neighbor firms.…”

Section: B Financial Forecastingmentioning

confidence: 99%

Quantum Machine Learning for Finance

Pistoia,

Ahmad,

Ajagekar

et al. 2021

Preprint

View full text Add to dashboard Cite

Quantum computers are expected to surpass the computational capabilities of classical computers during this decade, and achieve disruptive impact on numerous industry sectors, particularly finance. In fact, finance is estimated to be the first industry sector to benefit from Quantum Computing not only in the medium and long terms, but even in the short term. This review paper presents the state of the art of quantum algorithms for financial applications, with particular focus to those use cases that can be solved via Machine Learning.

show abstract

Section: B Financial Forecastingmentioning

confidence: 99%

Quantum Machine Learning for Finance

Pistoia,

Ahmad,

Ajagekar

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…A non-parametric machine learning technique, random forest, however, does significantly improve forecast accuracy and the ability to generate abnormal returns. Easton et al (2021) then use a k-nearest neighbour model approach to forecast a firm's annual earnings. They approach that Easton et al (2021) take is to match a firm's recent earnings to earnings histories of comparable firms, and then extrapolate the forecast from the comparable firms' lead earnings.…”

Section: Financial Statement Analysismentioning

confidence: 99%

“…Easton et al (2021) then use a k-nearest neighbour model approach to forecast a firm's annual earnings. They approach that Easton et al (2021) take is to match a firm's recent earnings to earnings histories of comparable firms, and then extrapolate the forecast from the comparable firms' lead earnings. They demonstrate this approach is able to generate out-ofsample forecasts that are more accurate than those generated by a random walk.…”

Section: Financial Statement Analysismentioning

confidence: 99%

“…They demonstrate this approach is able to generate out-ofsample forecasts that are more accurate than those generated by a random walk. An issue highlighted in Easton et al (2021) that applies to the developing machine learning literature in general, is that the process of developing forecasts is devoid of theory. Other than allowing for a computer to identify historical trends, this approach does not inform practitioners or researchers how to improve the process of fundamental analysis.…”

Section: Financial Statement Analysismentioning

confidence: 99%

See 1 more Smart Citation

Financial statement analysis: a review and current issues

Jackson

2021

CFRI

View full text Add to dashboard Cite

PurposeThe literature on financial statement analysis attempts to improve fundamental analysis and to identify market inefficiencies with respect to financial statement information.Design/methodology/approachIn this paper, the author reviews the extant research on financial statement analysis.FindingsThe author then provides some preliminary evidence using Chinese data and offer suggestions for future research, with a focus on utilising unique features of the Chinese business environment as motivation.Originality/valueThe author notes that there has been no work that the author could locate specifically on Chinese FSA research. The unique business environment in China, relative to the US where the vast majority of this work has been conducted, should motivate any studies, especially given the author documents the robust finding in terms of the mean reversion in profitability.

show abstract

“…Binz et al (2020) apply a deep-learning model to Nissim and Penman's (2001) structural profitability framework to predict the rate of return on capital employed (ROCE). They report that machine learning outperforms models based on linear estimation and a random walk (see also Easton et al, 2021;You & Cao, 2021).…”

mentioning

confidence: 99%

Machine learning and the prediction of changes in profitability

Jones

Moser

Wieland

2023

Contemporary Accting Res

View full text Add to dashboard Cite

This study uses machine learning methods to predict next‐period change in profitability based on a model proposed by Penman and Zhang (2004; “PZ”). We find that new machine‐learning methods predict out of sample substantially better than traditional regression methods and provide richer interpretations about the role and impact of different predictor variables through their nonlinear relationships and interaction effects. For example, our results contrast with previous research by showing that both components of the DuPont decomposition (change in profit margin and change in asset turnover) are informative of next‐period changes in profitability. Our results are robust across different performance metrics, alternative machine‐learning models, and software. Further, an unconstrained machine‐learning model using a larger feature space could not significantly improve on the performance of the PZ model. PZ variables alone accounted for most of the explanatory power of the unconstrained model, suggesting the PZ model is both well specified (in terms of feature selection) and robust in higher dimensional settings. With respect to the economic significance of this information, we find mixed results. The market appears to adjust its expectations more in line with the machine learning predictions relative to the PZ model but the portfolio returns are not significantly different.This article is protected by copyright. All rights reserved.

show abstract

Forecasting Earnings Using k-Nearest Neighbor Matching

Cited by 6 publications

References 30 publications

Quantum Machine Learning for Finance

Quantum Machine Learning for Finance

Financial statement analysis: a review and current issues

Machine learning and the prediction of changes in profitability

Contact Info

Product

Resources

About