Efficient Sailboat Price Prediction using Linear, Boosting and Deep Learning Models

Résumé fourni par la source

The recent increase in the popularity of sailboats calls for efficient prediction of sailboat prices, a feature that would help buyers, sellers, businesses, and investors. Machine Learning (ML) has been identified as an efficient tool for price prediction tasks. In this paper we propose new, efficient sailboat price prediction methodologies by employing various machine learning (linear, boosting) and deep learning techniques. The linear models used were linear regression, decision tree, random forest, support vector regression, and K nearest regressor; the boosting models used were AdaBoost, CatBoost, and XGBoost; and the deep learning models used were multilayer perceptron and 1-dimensional Convolutional Neural Networks. After training all our models, test results demonstrate great performance, with the highest R2score being 1-dimensional Convolutional Neural Network’s 0.887.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.