Machine Learning for Recommending Consumer Electronics
Machine Learning for Recommending Consumer Electronics

Summary/Abstract: This research examined the influence of Machine Learning on consumer electronics recommendations through a mobile application in Trujillo. A system based on the Random Forest algorithm was developed to suggest categories and display products according to predictions. Three indicators were analysed: number of recommendations, recommendation effectiveness, and average search time. Using a true experimental design with 190 records per group, the Mann–Whitney test (p = 0.001) revealed statistically significant differences. The results show that the use of Machine Learning improved the user experience by increasing the number of recommendations, enhancing their perceived usefulness, and reducing search time. These findings highlight the practical value of machine learning–based recommender systems for e-commerce platforms, as they can support more efficient product discovery and improve decision-making processes for both users and online retailers.

• Details
• Contents