Implementation of PC Algorithm to the Incidence Factor of Stunting Disease

Stunting is a very serious problem with nutritional conditions. The prevalence of stunting in Indonesia is still quite high at 21.9% in 2018 with an average of children under the age of 5, in 2019 it decreased by 21.6% in 2022. However, the decline needs to be emphasized again. Diverse sciences and technologies can be applied such as machine learning and deep learning. However, the algorithm cannot deeply see the causal relationship between input and output variables. The purpose of this study is to determine the relationship between the variables of stunting incidence using the Peter-Clark Algorithm. The data used in the study contained eight variables. The results of the study obtained a causal model consisting of 10 directed relationships and 1 bidirectional relationship 10 directed relationships. From this study, it can be concluded that the incidence of stunting can be influenced by several factors, including exclusive breastfeeding, weight at birth, height at birth and during the measurement period. Based on the model, it can be projected to be a concise guide for researchers to perform causal modeling, as well as choose an appropriate approach to the problem of interest.