Polymer-based composite material optimization is a key technology for achieving the desired thermal man
agement in heat conduction sheets used in electronics and aerospace. Diamond particles are widely used as
thermally conductive fillers in a liquid of poly di-methyl siloxane (PDMS) matrix because of their unique ther
mophysical properties. Electrical alignment is a powerful approach for filler alignment to achieve higher thermal
conductivity. Meanwhile, practical experiments require substantial time, resources and consumable energy due
to extensive testing. Therefore, it is essential to develop a highly robust predictive model for estimating thermal
conductivity. This paper proposes a data-driven-based model that investigates a novel decision tree (DT)
regression model for predicting thermal conductivity based on electrical alignment parameters, aiming to
identify the optimal experimental conditions that achieve higher thermal conductivity. In this study, electrical
alignment parameters, namely voltage, frequency, and rotational speed, are selected as descriptors for modelling
and computing thermal conductivity. Correlation and multicollinearity analyses are conducted to evaluate the
relationships among these descriptors. Three machine learning approaches, including Decision Tree, Random
Forest (RF), and Gradient Boosting Decision Tree (GBDT), are investigated alongside six empirical regression
models. The predictive model-based refined DT achieves high accuracy with the lowest mean square error of
0.0004 and a higher coefficient of determination (R-squared) of 0. 9751on testing data, respectively. This in
dicates that the model is capable of accurately predicting the thermal conductivity of hybrid nanofluids over a
wide range of hybrid nanoparticle combinations with high closeness to the experimental records. This predictive
model condition highlights the potential of DT-based method to precisely compute the thermal conductivity of
PDMS-diamond composite based on the applied electrical alignment parameters.