<![CDATA[The increasing popularity of e-commerce poses a new challenge to provide customers with a more personalized and effective shopping experience. In situations like this, product recommendations are very important to increase consumer satisfaction and increase sales. Using Random Forest and Boosting ensemble techniques, this research introduces a method for e-commerce product recommendation based on user review analysis. The Aim is to test the Random Forest algorithm with several boosting techniques for ensemble learning. The results show that the Random Forest method combined with the Xgboost technique can provide product recommendations that are 87.25% more accurate and relevant than other boosting techniques. In precision analysis, Random Forest-XGBoost achieved a higher accuracy of 90% compared to other boosting techniques. Additionally, the combined use of Boosting and Random Forest techniques improves the model's performance in handling complexity and variation in e-commerce product reviews.]]>
Copyrights © 2024
