Tariff Rate Prediction for Truckload Based on Predictive Analysis using Machine Learning

  • Arulkumar V, Agalya S, Gokul Chakkaravarthi S, Gokula Priya E

Abstract

A tariff rate is a price for transporting certain freight from source to the destination. The amount is based on the form of the freight, the mode of transport, the weight of the cargo and the distance to the destination of delivery. Of all products subject to tariffs measured on all imported commodities, the simple mean imposed tariffs in the un-weighted average of effective rates imposed for all products. Less-than-truckload is used for packing smaller freight trucks, in single trucks LTL carriers hold several shipments for numerous customer. The combination of the multiple cargo owner’s cargoes in one truck decrease the expense that each cargo owner has to pay. LTL shipping provides substantial savings over sending a dedicated truck with the same load. Specific rates have been converted to their ad valorem (An ad valorem tax is charged by state and municipal governments, and it is based on the assessed value of a product) equivalent rates and have been included in the calculation of simple mean tariffs to take the truck travelling details and its travelling cost to predict the truck overall travelling cost with tariff rate. We can collect the details from real time field. Applying regression method for prediction of tariff rate, the algorithmic approach involves supervised learning along with linear regression, support vector regression, random forest regression, and decision tree regression. Using this entire algorithm to find the best one for prediction. The python language with some standard libraries is used for model predictions based on data set value. Since users cannot run this model by using python idle there comes the user dependency lag.  For effective usage of this model by end-users on-site application is designed so that users can directly pass values from application to python code and get the accurate value for the entity.

Published
2020-05-20
How to Cite
Arulkumar V, Agalya S, Gokul Chakkaravarthi S, Gokula Priya E. (2020). Tariff Rate Prediction for Truckload Based on Predictive Analysis using Machine Learning. International Journal of Advanced Science and Technology, 29(9s), 5477 - 5482. Retrieved from https://sersc.org/journals/index.php/IJAST/article/view/18065