Working capital financing and firm performance: a machine learning approach

Mahmood F., Ahmed Z., Hussain N., Ben-Zaied Y.

Review of Quantitative Finance and Accounting, vol.65, no.1, pp.71-106, 2025 (ESCI, Scopus) identifier

  • Nəşrin Növü: Article / Article
  • Cild: 65 Say: 1
  • Nəşr tarixi: 2025
  • Doi nömrəsi: 10.1007/s11156-023-01185-w
  • jurnalın adı: Review of Quantitative Finance and Accounting
  • Jurnalın baxıldığı indekslər: Emerging Sources Citation Index (ESCI), Scopus, IBZ Online, International Bibliography of Social Sciences, ABI/INFORM, Business Source Elite, Business Source Premier, EconLit
  • Səhifə sayı: pp.71-106
  • Açar sözlər: Decision tree regression, Principal component analysis, Profitability, Random forest regression, Short-term borrowings, Working capital finance
  • Açıq Arxiv Kolleksiyası: Məqalə
  • Adres: Bəli

Qısa məlumat

Companies always try to balance the risk and return on their investments, finances, and daily operations. This study presents the moderating role of ownership status, company size, and leverage level while investigating the relationship between short-term-borrowings and profitability in six sectors of Chinese firms. Contrary to the prevalent literature, the current study creates master proxies, via principal component analysis, for major analysis. Two machine learning techniques, decision tree regression, and random forest regression algorithms, are compared with the fixed effect model to find the better estimation approach. The findings confirm the existence of an inverted U-shaped relationship between working capital finance and profitability in six sectors except the textile, significantly affected by ownership structure, company size, and leverage level. Various policy implications are suggested for company managers as well as lending organizations.