13-14 October, started the AWS Summit China 2022 with the topic “Build with Freedom, Explore the Infinite” (official Chinese name: 自由构建、探索无限). Tech experts and companies gathered at the summit to share their advanced practices and insights in cloud computing from a global perspective, where ShoplazzaThe CTO of , Bing Xia, gave a speech about its AI-powered recommendation technology for cross-border e-commerce.
Hosted by Amazon Web Services (AWS), the Summit is the largest annual technology event in China and a benchmark in global cloud computing. As the world’s leading shopping cart SaaS company, Shoplazza was invited to the summit to share its best practices with advanced product features and technology. Shoplazza has provided various enterprise-level solutions to more than 360,000 merchants worldwide, including well-designed e-commerce store themes, automated order management and flows, multi-channel marketing campaigns, and secure and easy-to-follow payment processes.
In recent years, branding has played an important role in e-commerce. More and more cross-border traders have embraced the DTC model and moved to more refined business operations and management to grow the business. And the “AI-powered recommendation” is one of the crucial features that need to be implemented in the online store.
“On a global scale, AI-powered recommendation is an essential technology to integrate to improve sales revenue and customer shopping experience.” Bing, CTO of Shoplazza, said, “But it’s difficult for small and medium-sized businesses ( SMEs) to implement AI solutions intended for large companies. SMB retailers need to invest additional effort and time in manually optimizing product recommendation, which takes a lot of time and reduces operational efficiency. In addition, it is not easy for customers to be satisfied with what they see in the recommendations. Based on this situation, we want to provide a technology solution for AI-powered recommendation that can be applied to all merchants of any size, which reduces costs and improves efficiency.”
Bing explained Shoplazza’s AI and machine learning system in 5 phases, including (1) data retrieval, (2) triggers, (3) pre-ranking, (4) ranking, and (5) re-ranking. Shoplazza makes every effort to handle data to ensure that every process runs efficiently and smoothly. Due to the enormous amount of data that needs to be processed, e.g. However, the standalone TensorFlow cannot be trained quickly. Additionally, distributed machine learning on Spark has several shortcomings such as: B. slow training and high costs.
To solve the vulnerabilities, Shoplazza uses the data flow and processing power of Amazon EMR and Amazon SageMaker and combines all processes including sampling, feature training and estimation for the data flow of Shoplazza’s recommendation engine. This combined data flow technique enables more efficient data processing and machine learning capabilities. “Based on the generated examples, model training is performed in the SageMaker platform and real-time reasoning is deployed. When the user requests recommendations, the prediction can connect user features and product features in real-time and display the feature extraction plugin to generate samples by asking SageMaker to get the score and display the sorting result on the web page.” Bing led the detailed dataflow implementation of AI-powered recommendations with SageMaker.
With Amazon EMR and Amazon SageMaker, Shoplazza simplifies the management of big data and machine learning infrastructures by integrating data analysis and machine learning for cost-effective results.” Up to 300 GB of training data only takes 2 hours, the time is reduced by around 10 Hours are reduced and the performance of the product recommendation system is improved by 6 times. To better serve our merchants, we continue to implement and develop AI technology to help them thrive globally,” said Bing.
Bing added, “AI and machine learning are the most transformative technologies in the world today, and they are instrumental in improving customer experiences and increasing business productivity. Going forward, Shoplazza will continue to work with AWS to integrate machine learning of recommendations into product search, content understanding, merchant selection, e-commerce risk control, and other business operations. Technological innovations will solve the problems faced by retailers during store operations.”
As the world’s leading eCommerce SaaS platform, Shoplazza will remain dedicated to providing innovative solutions and sharing successful market expansion practices. At the same time, Shpplazza will continue to stay”Open for more‘ to perfect its partner ecosystem and partner with AWS to enable cross-border merchants to start anywhere with all-in-one solutions to go global through advanced technology, product innovation and modern data strategy.