Scholarlink

Predicting container throughput through a port is critical for effectively planning and optimizing port operations, enhancing efficiency, reducing costs and effective resource allocation and ultimately contributing to the competitiveness and resilience of port ecosystems. In this study five different machine learning models are used to model and train the container throughput of agro products through Cochin port. The daily vise variation of agro products during 2018–2022 were used. The model developed are used to forecast the agro product volume of containers for the next five years with validation of actual data in the year 2023. Results shows that among the five different ML models, linear regression is the most suitable candidate for the time series forecasting of agro products export through Cochin port.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Time Series Prediction of Port Container Throughput Using Machine Learning Models

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • T. V. Rameesha,
  • Goutham Sarang,
  • Alosh Denny,
  • Augustine Anish,
  • Tanu Shree,
  • P. E. Jayalakshmi

摘要

Predicting container throughput through a port is critical for effectively planning and optimizing port operations, enhancing efficiency, reducing costs and effective resource allocation and ultimately contributing to the competitiveness and resilience of port ecosystems. In this study five different machine learning models are used to model and train the container throughput of agro products through Cochin port. The daily vise variation of agro products during 2018–2022 were used. The model developed are used to forecast the agro product volume of containers for the next five years with validation of actual data in the year 2023. Results shows that among the five different ML models, linear regression is the most suitable candidate for the time series forecasting of agro products export through Cochin port.