Recent years have seen the increasing popularity of e-commerce platforms which have changed the shopping behaviour of customers. Valuable data from products, customers, and purchases on such e-commerce platforms enable the delivery of personalized shopping experiences, customer targeting, and product recommendations. We introduce a novel Vietnamese dataset specifically designed to examine the recommendation problem in e-commerce platforms, focusing on face cleanser products with 369,099 interactions between users and items. We report a comprehensive baseline experimental exploration into this dataset from content-based filtering to attribute-based filtering approaches. The experimental results demonstrate an enhancement in performance, with a 27.21% improvement in NDCG@10 achieved by incorporating a popularity score and content-based filtering, surpassing attribute-based filtering. To encourage further research and development in e-commerce recommendation systems using this Vietnamese dataset, we have made the dataset publicly available at https://github.com/linh222/face_cleanser_recommendation_dataset.