This article presents a comprehensive study on developing a predictive product pricing model using LightGBM, a machine learning method optimized for regression challenges in situations with limited historical data. It begins by detailing the core principles of LightGBM, including gradient descent, and then delves into the method's unique features like Gradient-based One-Side Sampling (GOSS) and Exclusive Feature Bundling (EFB). The model's efficacy is demonstrated through a comparative analysis with XGBoost, highlighting Light-GBM's enhanced efficiency and slight improvement in prediction accuracy. This research offers valuable insights into the application of LightGBM in developing fast and accurate product pricing models, crucial for businesses in the rapidly evolving data landscape.