Optimizing Goods Placement in Logistics Transportation using Machine Learning Algorithms based on Delivery Data

Abstract

This study addresses the challenge of predicting the optimal placement of goods for expeditionary transportation. Efficient placement is crucial to ensure that goods are transported in a manner that maximizes space and minimizes the risk of damage. This study aims to develop a prediction system using the K-Nearest Neighbor (KNN) method, which is based on expert data from expedition vehicles. To evaluate the effectiveness of the KNN method, the researcher compared it with the Support Vector Machine (SVM) method. By doing so, they sought to determine which method delivers more accurate predictions for the optimal placement of goods. The test results revealed that the KNN method outperformed SVM, achieving a higher accuracy of 95.97% compared to SVM's 92.85%. Additionally, KNN demonstrated a lower Root Mean Square Error (RMSE) of 0.18, indicating more precise predictions, while SVM had an RMSE of 0.271. These findings suggest that KNN is the more effective method for predicting the optimal placement of goods in expeditionary transportation.

Keywords

• classification
• goods placement
• k-nearest neighbor (knn)
• support vector machine (svm)