Abstract

Accurate diamond price prediction is critical for stakeholders in the jewelry industry. This study presents a comprehensive approach to predicting diamond prices using various regression models. Based on the diamond dataset sourced from diamond market data, an exhaustive analysis was conducted, including data normalization, evaluation of multiple regression models, and optimization of the Random Forest model. The methods applied in this research involve detailed preprocessing steps to handle missing values and normalize features, ensuring the robustness of the models. The results show that the Random Forest model, after optimization, outperforms other regression models in terms of prediction accuracy. This approach demonstrates how advanced machine learning techniques can be effectively utilized to estimate the value of diamonds, providing a practical tool for professionals in the sector. The findings underscore the potential of machine learning to enhance decision-making processes in the jewelry market.

Key words: Machine learning, diamond price prediction, regression analysis, optimization models.