The document proposes inducing predictive clustering trees (PCTs) to approximate numerical datatype property values in knowledge bases. PCTs perform multi-target regression by clustering individuals based on descriptive logic concept descriptions, then fitting a predictive model to each cluster. The approach is tested on datasets extracted from DBPedia, showing PCTs outperform alternative methods like terminological regression trees, k-NN, and linear regression in terms of accuracy and efficiency. Future work could explore new refinement operators, heuristics, and linear models at leaf nodes to further improve PCTs for predicting property values in semantic data.