Shopee is the leading e-commerce platform in Southeast Asia and Taiwan. It is a platform tailored for the region, providing customers with an easy, secure and fast online shopping experience through strong payment and logistical support.
Shopee aims to continually enhance its platform and become the region’s e-commerce destination of choice. Shopee has a wide selection of product categories ranging from consumer electronics to home & living, health & beauty, baby & toys, fashion and fitness equipment.
Shopee, a Sea company, was first launched in Singapore in 2015, and has since expanded its reach to Malaysia, Thailand, Taiwan, Indonesia, Vietnam and the Philippines. Sea is a leader in digital entertainment, e-commerce and digital financial services across Greater Southeast Asia. Sea's mission is to better the lives of consumers and small businesses with technology, and is listed on the NYSE under the symbol SE.
For more information, please visit https://shopee.sg
1) Introduction to Data Science by Xiangyu
Brief introduction to our Shopee Data Science team and relevant data science topics.
2) Knowledge Graph for Shopee Products by Sun Zhu
A knowledge graph is a type of graph-based knowledge representation. A high-quality knowledge representation is beneficial for many eCommerce functions, such as recommendation and search. The Shopee Data Science team has developed an in-house knowledge graph using state-of-the-art technologies and includes millions of Shopee products. In this talk, the speaker will introduce the fundamentals of Shopee's in-house knowledge graph, and discuss how it can be applied to Shopee's recommendation system.
3) OCR with Deep Attention Models by Mingming
OCR stands for Optical Character Recognition. It is a decades-old technology that allows machines to read numbers and characters from images. OCR technology has been applied to many aspects in eCommerce industries and corporate administrations, such as identity verification, payment receipt verification and document digitization. Traditional OCR techniques rely heavily on hand-crafted features and domain knowledge. Due to the recent surge of deep learning technologies, there have been quite a few deep learning models that enable more accurate and robust OCR applications, and these models are built in a data-driven and end-to-end manner. In this talk, the speaker will introduce a deep learning model called Attention OCR and elaborate on the concepts of some of its building blocks.
4) Virtual Makeovers by Kouwen
Virtual Makeovers is an application of Augmented Reality Technology. It has been widely integrated into many selfie apps such as BeautyCam Meitu which will augment people's beauty. At Shopee, virtual makeover can be used to enhance the sales of beauty products. Before buyers decide to buy specific lipsticks, foundation or other beauty products, they can “try on” the product to see the effect, which will also improve the user experience. In this talk, the speaker will introduce Shopee's virtual makeover solution pipeline and provide some demos.
Last updated on 25 Mar 2019 .