This study investigates the thermal conductivity of the Jordanian travertine rock, an important construction material, using the Hot Disk Transient Plane Source (TPS) 2200 technique. Thermal conductivity was correlated with the physical and engineering properties of the travertine through simple regression, multiple regression, and Artificial Neural Network (ANN) model to develop predictive relationships. To perform this study, 61 cylindrical core samples were extracted from different locations along the margins of the Dead Sea in Jordan and prepared with a diameter of 10 cm and height of 20 cm. The results indicated that the thermal conductivity ranged between 2.678 (W/(m*k)) to 3.407 (W/(m*k)) with an average approximately equal to 3 (W/(m*k)). The results showed that the thermal conductivity increases with increasing the density, hardness, rock strength, and P-wave velocity. On the other hand, the thermal conductivity decreases with porosity and water-absorbed capacity. The results showed that the ANN model outperformed other models in prediction accuracy. The developed models provide a foundation for estimating thermal conductivity based on basic physical properties, offering a cost-effective alternative to direct measurements for selecting suitable construction stones.