Comparer des méthodes

	Beneish M-Score : Détection de la manipulation des bénéfices	Analyse DuPont
Domaine	Finance	Finance
Famille	Regression model	Regression model
Année d'origine	1999	2008
Auteur d'origine	Messod Beneish	DuPont Corporation; Soliman
Type	Probabilistic forensic accounting model	Profitability decomposition framework
Source fondatrice	Beneish, M. D. (1999). The detection of earnings manipulation. Financial Analysts Journal, 55(5), 24–36.	Soliman, M. T. (2008). The use of DuPont analysis by market participants. The Accounting Review, 83(3), 823–853.
Alias	Beneish Model, M-Score Model, Earnings Manipulation Score, Beneish M-Skoru	DuPont Decomposition, DuPont Identity, Return on Equity Decomposition, DuPont Analizi
Apparentées	3	2
Résumé	The Beneish M-Score is a statistical model developed by Messod Beneish in 1999 to identify whether a company has manipulated its reported earnings. The model combines eight financial-statement ratios into a single composite score using coefficients estimated from a probit regression on a sample of detected earnings manipulators. A score above −2.22 indicates a heightened probability of manipulation, making the M-Score a widely used tool in forensic accounting and investment due-diligence.	DuPont Analysis is a financial performance framework that decomposes Return on Equity (ROE) into three multiplicative components: net profit margin, asset turnover, and the equity multiplier. Originally developed by engineers at DuPont Corporation in the early 1920s, the method gained renewed academic prominence through Soliman (2008), who demonstrated that market participants exploit DuPont decompositions to forecast future earnings and to distinguish sustainable from transient profitability.