Huang, Sieh-Chuen; Shao, Hsuan-Lei; Leflar, Robert B
Abstract: The doctrine of “best interests of the child” has guided courts in determining post-divorce child custody cases in Taiwan since the amendment of the Taiwan Civil Code in 1996. Amended Article 1055-1 of Taiwan’s Civil Code requires judges to consider factors such as “the age, sex, and wishes of the child” and “the age, occupation, character, health condition, economic condition, and life style of the parents.” Previous empirical studies have adopted descriptive statistics in analyzing court cases to determine which factors, as set out in Article 1055-1, are the ones judges tend to consider. However, these approaches do not clarify which factors judges consider primary.
This Article collects family court decisions from 2012 to 2017, involving 1,126 children whose parents were both Taiwanese and who both sought to acquire custody, in which Taiwanese district courts granted sole custody to the husband or the wife. The Article employs decision tree methodology, a commonly used machine learning techonology. To our knowledge, this is the first published application worldwide of machine learning to analysis of family court decisionmaking.
The Article concludes that the three most significant factors considered by judges in Taiwan are, first, which parent is the child’s current primary caregiver, followed by the wishes of the child and the judge’s assessment of the relative quality of each parent’s parent-child interaction. This result runs counter to widely held beliefs that parental gender and parents’ occupations and economic resources are prime factors in judges’ contemplation. This study should enable researchers to identify a particular custody case as either typical or exceptional. The study should also enable lawyers and parties to preliminarily evaluate probable outcomes of custody disputes, saving time and expense in case preparation.