<p>The study of Reiner–Rivlin fluid over a rotating surface with Newtonian heating is essential for observing the non-Newtonian fluid behavior in engineering and industrial processes. Moreover, rotating system arises in applications where rotation induces unique flow patterns that find applications in chemical mixers, turbo machinery, and cooling systems. In present study an incompressible steady-state hydrodynamic flow of Reiner–Rivlin fluid (RRF) over a stretchable rotating disk is examined. The axi-symmetric laminar boundary layer flow incorporates the impacts of Newtonian heating and temperature-dependent thermal conductivity. The flow governing equations are transformed into dimensionalized form by invoking similarity variables. The reduced self-similar system of ordinary differential equations is evaluated in numerical way by implementing Runge–Kutta–Fehlberg (RKF-45) method based on built-in Maple package. The dimensionless parameters are discussed graphically on flow and temperature profiles respectively. The moment coefficient, radial wall skin-friction, local Nusselt number, and volume flow rate are critically scrutinized at the disk surface against the physical quantities under consideration. Artificial neural network (ANN) model such as multi-layer forward neural network with propagation is used to obtain the predicted values of moment coefficient, radial wall skin-friction, local Nusselt number, and volume flow rate. It is found that Reiner–Rivlin fluid (RRF) parameter turn down the radial velocity field whereas such parameter augmented the thermal field and corresponding thermal boundary layer thickness. The effect of stretching enhancing the radial velocity profiles at the disk surface. The thermal boundary layer thickness is modified due to the enhancement of conjugate parameter. The ideal value for training, testing, and validation for the ANN model is achieved by attaining the correlation R-values equal to one.</p>