Abstract

Research investigating models for assessing new tractor pricing is notably scarce, despite its fundamental importance in conducting comprehensive cost analyses. This study aims to identify a model that is both user-friendly and robust, evaluating both parametric and Machine Learning-optimized non-parametric models. Among parametric models, the second-order polynomial model demonstrated superior performance in terms of R-squared (R2) of 0.97469 and a Root Mean Square Error (RMSE) of 15,633. Conversely, Machine Learning-optimized Gaussian Processes Regressions exhibited the most favorable overall R-squared (R2) of 0.99951 and a Root Mean Square Error (RMSE) of 2321. While the parametric polynomial model offers a solution with minimal mathematical and computational complexity, the non-parametric GPR model delivers highly robust outcomes, presenting stakeholders involved in new agriculture tractor transactions with superior data-driven decision-making capabilities.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call