This analysis used the backpropagation Levenberg-Marquardt technique coupled through neural networks (BPLMT-NN). The magnetohydrodynamic (MHD) viscous nanofluid flow due to the rotating disk (MHD-VNRD) through the slip effect was investigated. In the existence of a velocity slip condition, this communication investigated the boundary coating flow of viscous nanofluid under MHD conditions. The flow was produced by a disk that was revolving. A fluid effects electricity under the effect of a magnetic field that is transverse. The magnetic field that is generated is neglected when the magnetic Reynolds number is low. The properties of Brownian and thermophoresis motion were demonstrated using a nanofluid simulation. Hypotheses about the boundary coating and low magnetic Reynolds number were made while formulating the problem. To transform nonlinear partial differential equations into a scheme of ordinary differential equations, the similarity transformation was utilized. On the profiles of velocity, temperature, and concentration, a data set for the suggested (BPLMT-NN) was created for the impacts of several important parameters and was illustrated via the explicit Runge-Kutta technique. Using the (BPLMT-NN) testing, training, and validation approach, the estimated result of various situations was endorsed, and the suggested model was evaluated for fitness. After that, the proposed (BPLMT-NN) was validated using mean square error (MSE), regression analysis, and histogram investigations. The novelty of the proposed BPLMT-NN technique has various applications, such as disease diagnosis, robotic control systems, ecosystem evaluation, etc. We conducted analyses of some statistical data like gradient, performance, and epoch of the proposed fluid model. Based on closeness, as well as recommended and reference results, the suggested approach has made a distinction with precision level varying from ${10}^{-09}$ to ${10}^{-11}$.