Machine Learning can be successfully utilized in geotechnical designing applications, where vulnerability is a portion of nature, to create a vigorous predictive model foundation for designing parameters/behaviors. Formerly, geotechnical plan parameters were not continuously straightforwardly measured from a research facility and in-situ tests or maybe frequently assessed from observational or numerical relationships that are created from regression fitting to a dataset. ML models were created to train a nearby dataset. The developing volume of data databases presents openings for progressed information examination methods from machine learning inquiries. Applied applications of ML are exceptionally distinctive from hypothetical or observational studies. The feasible applications of ML were examined and created a proposition for a seven-step preparation that can direct viable applications of ML in design. In this work, an ML model was developed to predict pile behaviors based on a cone penetration test (CPT). The ML model was used to develop approximately 500 data sets from the available literature. The ML model beats the conventional techniques when the predictions made by ML are compared to those provided by several conventional approaches in the study.