We examine the impact of two types of earnings management, accruals and real activities manipulation, on bankruptcy prediction models. Consider that the form of engaging on earnings management might characterize firms’ financial condition, we hypothesize and find that the special information extracted from earnings management models, which encompass potential manipulations, serves to improve the accuracy of bankruptcy prediction models. We further provide evidences that when potential accruals manipulation is measured, it allows an improvement of bankrupt firms, while real activities measures, especially sales manipulation, enhance the prediction improvement of non-bankrupt firms. Our finding suggests that failed firms are more likely to engage on accruals manipulation, while healthy firms do it on real activities manipulation. As a result, this study contributes to the literature by analyzing a novel explanatory variable, earnings management variable, to predict bankruptcy that can overcome financial alteration and can be applied to any type of firms.