Diagnosing Assets Impairment by Using Random Forests Model

Abstract

This study develops a diagnosing model to examine the outcomes of assets write-off in enriching the literatures of assets impairment. Prior studies employed the Logit, linear and Tobit regression models to classify the determination of assets impairment and to diagnose the magnitude of the impairment, respectively. However, the drivers of assets write-off are somewhat complicated explicitly or implicitly, these models are unlikely to provide fairly satisfactory results. To improve the diagnosis, the Random Forests model is used for the classification determining and the magnitude diagnosing of assets impairment in this study. The result reveals that the Random Forests model outperforms the Logit and linear regression models in each case with variables selected by individual wrapping approach. This study also demonstrates diagnostic checks for both models with similar selected variables. The results are robust to these various specifications.

Does the Mark-to-Model Fair Value Measure Make Assets Impairment Noisy?: A Literature Review

“…To determine the impact of hypothesised drivers on the write-off decision, Garrod et al [31] estimated four separate logistic regressions for the companies included in the total sample. Mathematical models, such as the random-forest (RF) model provided by Chen and Wu [32], have also focused on the asset impairment drivers. The diagnosis of the asset impairment factors, presented by Chen and Wu [32] used the RF model, showing a new approach to calculating asset impairment other than regression analyses.…”

“…Mathematical models, such as the random-forest (RF) model provided by Chen and Wu [32], have also focused on the asset impairment drivers. The diagnosis of the asset impairment factors, presented by Chen and Wu [32] used the RF model, showing a new approach to calculating asset impairment other than regression analyses. The magnitude of potential determinants, including financial information, the economic environment, and management incentives, complicates the process of verifying the asset impairment test's correctness.…”

“…A change in management is a relevant systematic factor demonstrated in the articles. This dimension was mentioned by Bens [25], Giner and Pardo [30], Chen and Wu [32], Cotter et al [35], AbuGhazaleh et al [36], Lapointe-Antunes et al [38], and Bond et al [46]. The results in those articles suggest that the decision about impairment recording is more associated with managers' incentive to convey expectations about their good performance, rather than presenting reliable information to the stakeholders about the company's financial condition.…”

“…On the other hand, the research sample contained two reports showing no influence in management incentives on write-off announcements. Chen and Wu [32], analysing the factors using the random-forest model, showed that more weight is placed on financial information than on the economic influence or management incentives. Kabir and Rahman [37] also indicated a weak association between contracting incentives and goodwill impairment.…”

Predictors determining the potential of inland valleys for rice production development in West Africa

“…In medicine, extensions of this method have been proposed, and aimed at identifying variables important to the trait of interest (Barco et al, 2012;Boulesteix, Janitza, Kruppa, & König, 2012;Casanova et al, 2014;Chang & Yang, 2013;Chen & Ishwaran, 2012;Chen & Wu, 2012;Díaz-Uriarte & Alvarez de Andrés, 2006;Tang et al, 2009;Zhou et al, 2010). In ecology, Random Forests has been used to deliver some significant results through satellite images using remote sensing and GIS techniques (Cutler et al, 2007;Gislason et al, 2006;Li, Tran, & Siwabessy, 2016;Loosvelt et al, 2012;Mellor, Haywood, Stone, & Jones, 2013).…”