Exploring Machine Learning Methods Towards Effective Transportation based Predictive Model

Transportation is the backbone for every industry with the rise in having everything at our doorstep. Transportation is a significant domain as it is required for transferring goods to and fro from one place to another. Machine Learning is gaining a lot of popularity in recent times because of its immeasurable power of problem solving. Regressive methods that are a domain of machine learning algorithms have been proven to be successful because they have a strong mathematical foundation and can be compared against other approaches to find out which approach is the most compatible to perform on the dataset to give the finest result. By conducting a comparative analysis of error metrics, including Confusion Matrix, Accuracy, Precision, Recall we attempt to evaluate the effectiveness and robustness of the model. This study aims to contribute to the betterment of predictive models in a transportation dataset and offers insights into the limitations of Machine Learning algorithms on the selected model through which we find that Logistic regression works best on our model with an accuracy of 0.65 and Lasso was the most unfit regression for our dataset.