Prediction of the Sustainability Index in Family Firms Using Explainable Artificial Intelligence

Abstract

The first objective of the article is to develop a method for predicting the level of sustainability in family firms based on the dimensions of socioemotional wealth. To achieve this goal, the following machine learning algorithms were employed: Support Vector Regression (Linear Kernel), Support Vector Regression (Radial Basis Function Kernel), Decision Tree Regressor (DTR), K-Neighbours Regressor (KNR), Random Forest Regressor (RF), and Linear Regression (LR). The second objective was to determine the impact of individual socioemotional wealth dimensions on the sustainability index of family businesses. To this end, the Permutation Feature Importance (PFI) method, classified under Explainable Artificial Intelligence (XAI), was used. The study’s results on Polish family firms revealed that the SEW dimension most strongly influencing the sustainability index is the active promotion of initiatives for the local community.