Recent seismic events have produced extensive documentation of the occurrence of lateral spreading due to liquefaction, which has severely destroyed infrastructure and structures. It is feasible to forecast their detrimental consequences in form of lateral spreading using soft computing. The present study is based on two powerful machine learning (ML) algorithms: the Artificial Neural Network (ANN) model and the Adaptive Neuro-fuzzy Inference System (ANFIS) model, along with the MLR model. These will be used with the “MATLAB” software based on 200 observations of sloping ground conditions from different locations in Bihar’s Zone-V, which is a very seismic area. The Youd [16] approach is used to estimate the horizontal lateral displacement (Dh). The study’s parameters consider significant parameters which include layer thickness (T15), average grain size (D5015), fine content (F15), source distance (R), ground slope (S), magnitude of the earthquake (M), and horizontal lateral displacement (Dh). Statistical measures, such as the root mean square error (RMSE), correlation coefficient, coefficient of determination, and Nash–Sutcliffe efficiency coefficient are used to evaluate the performance of the ANN and ANFIS models. For the Sitamarhi site, a maximum and minimum lateral displacement of 38 mm and 18 mm, respectively, are noted. Additionally, a maximum and minimum lateral displacement of 16.5 mm and 3 mm, respectively, are noted for the Darbhanga site. Also, it is found that ANFIS is relatively superior to the ANN techniques, considering the accuracy of its results in terms of the prediction errors obtained. The parametric study shows that the liquefiable layer thickness (T15), source distance (R) and mean grain size (D5015) have major contribution in influencing the predicted displacements.