THE NEXUS BETWEEN CASH CONVERSION CYCLE, WORKING CAPITAL FINANCE, AND FIRM PERFORMANCE: EVIDENCE FROM NOVEL MACHINE LEARNING APPROACHES

Faisal Mahmood (), Umeair Shahzad (), Ali Nazakat (), Zahoor Ahmed, Husam Rjoub and Wing-Keung Wong
Additional contact information
Faisal Mahmood: School of Economy & Management, Harbin Institute of Technology, Harbin 150001, P. R. China
Umeair Shahzad: School of Management, Ocean University, Qingdao 266100, P. R. China
Ali Nazakat: School of Management, Iqra University, Islamabad, Pakistan
Zahoor Ahmed: Department of Accounting and Finance, Faculty of Economics and Administrative Sciences, Cyprus International University, Mersin, Haspolat 99040, Turkey5Department of Economics, School of Business, AKFA University, Tashkent, Uzbekistan

Annals of Financial Economics (AFE), 2022, vol. 17, issue 02, 1-44

Abstract: This study examines the moderating role of the cash conversion cycle (CCC) while investigating the effects of working capital finance (WCF) on firm performance. Using more than 18000 observations from Chinese manufacturing firms, we computed several proxies for each variable of the study and merged these proxies via Principal Component Analysis (PCA) to create one master proxy for each variable. These master proxies contain all the essential information of individual proxies. Hence, they are more useful in producing reliable results than individual proxies. We also compared the predicting power of 15 econometric and machine learning estimators to select the best estimator. Based on the highest R2 value, we used two machine learning estimators, K-Nearest Neighbors (KNN), and Artificial Neural Networks (ANN) for subsequent analysis. To strengthen the empirical analysis, we employed another machine learning technique, i.e., the Bagging method, which is an ensembling technique that uses multiple estimators simultaneously to improve the accuracy and generalization of results. We used the Bagging method with 50KNN estimators. The findings unfold that the sensitivity level of firm performance to short-term debts shifts when the CCC period of firms fluctuates. More precisely, the WCF–performance relationship in firms with extended CCC is more sensitive compared with this relationship in the full sample. On segregating the three elements of CCC, we observe that the WCF–performance relationship in firms carrying extended account receivable (AR) days or extended Inventory days is more sensitive than the full sample. These findings are useful for firms’ management for revising the optimal level of short-term debts according to CCC fluctuation. Also, the lending agencies can use these results for the assessment of firms’ risk levels and adjustment of the interest rate.

Keywords: Working capital finance; firm performance; cash conversion cycle; principal component analysis; k-nearest neighbors; artificial neural networks; Bagging method (search for similar items in EconPapers)
Date: 2022
References: Add references at CitEc
Citations: View citations in EconPapers (5)

Downloads: (external link)
http://www.worldscientific.com/doi/abs/10.1142/S2010495222500142
Access to full text is restricted to subscribers

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:wsi:afexxx:v:17:y:2022:i:02:n:s2010495222500142

Ordering information: This journal article can be ordered from

DOI: 10.1142/S2010495222500142

Access Statistics for this article

Annals of Financial Economics (AFE) is currently edited by Michael McAleer

More articles in Annals of Financial Economics (AFE) from World Scientific Publishing Co. Pte. Ltd.
Bibliographic data for series maintained by Tai Tone Lim ().