"Zalando is an online shopping platform. You can think of it as European version of Amazon. Basically, people come to Zalando to buy shoes, clothes, lifestyle products, beauty products."
"The user journey starts from the landing page of the website or opening page of the application. It's very important what kind of content we show there."
"We developed and trained a graph neural network to improve our existing recommender system, to make it more personalized, to optimize for longer-term metrics."
"I will describe how we prepare the data, how we convert tabular data into a graph, what specific differences graph representation brings."
Zalando, an online shopping platform, developed a graph neural network to improve its recommender system. The focus was on personalizing recommendations and optimizing for long-term metrics. The process involved converting tabular data into a graph format, which presented unique challenges during training. The presentation covers the setup of the recommender system, data preparation, training pitfalls, and offline evaluation results. Future steps for further development in this area are also suggested.
Read at InfoQ
Unable to calculate read time
Collection
[
|
...
]