The Beneish model is a statistical model that uses financial ratios calculated with accounting data of a specific company in order to check if it is likely (high probability) that the reported earnings of the company have been manipulated.
The Beneish M-score is calculated using 8 variables (financial ratios):
(DSRI) DSRI = (Net Receivables<sub>t</sub> / Sales<sub>t</sub>) / (Net Receivables<sub>t-1</sub> / Sales<sub>t-1</sub>)
GMI = [(Sales<sub>t-1</sub> - COGS<sub>t-1</sub>) / Sales<sub>t-1</sub>] / [(Sales<sub>t</sub> - COGS<sub>t</sub>) / Sales<sub>t</sub>]
AQI = [1 - (Current Assets<sub>t</sub> + PP&E<sub>t</sub> + Securities<sub>t</sub>) / Total Assets<sub>t</sub>] / [1 - ((Current Assets<sub>t-1</sub> + PP&E<sub>t-1</sub> + Securities<sub>t-1</sub>) / Total Assets<sub>t-1</sub>)]
SGI = Sales<sub>t</sub> / Sales<sub>t-1</sub>
DEPI = (Depreciation<sub>t-1</sub>/ (PP&E<sub>t-1</sub> + Depreciation<sub>t-1</sub>)) / (Depreciation<sub>t</sub> / (PP&E<sub>t</sub> + Depreciation<sub>t</sub>))
SGAI = (SG&A Expense<sub>t</sub> / Sales<sub>t</sub>) / (SG&A Expense<sub>t-1</sub> / Sales<sub>t-1</sub>)
LVGI = [(Current Liabilities<sub>t</sub> + Total Long Term Debt<sub>t</sub>) / Total Assets<sub>t</sub>] / [(Current Liabilities<sub>t-1</sub> + Total Long Term Debt<sub>t-1</sub>) / Total Assets<sub>t-1</sub>]
TATA = (Income from Continuing Operations<sub>t</sub> - Cash Flows from Operations<sub>t</sub>) / Total Assets<sub>t</sub>
The formula to calculate the M-score is:
The threshold value is -1.78 for the model whose coefficients are reported above. (see Beneish 1999, Beneish, Lee, and Nichols 2013, and Beneish and Vorst 2020).
A 2023 research paper uses an aggregate score of many companies to predict recessions. It finds that the score in early 2023 is the highest in some 40 years.
Enron Corporation was correctly identified 1998 as an earnings manipulator by students from Cornell University using M-score. Noticeably, Wall Street financial analysts were still recommending to buy Enron shares at that point in time.