Zalando publishes its RESTful API and Event Guidelines
It’s a bit off-topic, but since APIs have some relevance for recommender systems, this is worthwhile news*: Zalando – one of the world’s largest fashion retailers and quite active in the recommender-system community – released its guidelines for the development of RESTful APIs.
I know from my own experience (e.g. through guest lectures in my classes given by developers of Zalando), that Zalando considers APIs as absolutely critical for business success, and they spend a lot of time improving their APIs. I also designed some APIs for recommender systems myself (e.g. Mr. DLib and Darwin & Goliath), and know firsthand how challenging this is. Their guidelines hence, are a very nice read for anyone who is interested in APIs. Read more: https://github.com/zalando/restful-api-guidelines
* I am not sure how new this news is. I just stumbled upon it, and it may be that the guidelines are already public for a long time.
TensorFlow introduces a new ‘end-to-end’ solution for on-device recommendations with TFLite
HetSeq: Training BERT on a random assortment of GPUs [Yifan Ding et al.]
NeuRec: An open source neural recommender library [Bin Wu et al.]
About The Author
Joeran Beel
I am the founder of Recommender-Systems.com and head of the Intelligent Systems Group (ISG) at the University of Siegen, Germany https://isg.beel.org. We conduct research in recommender-systems (RecSys), personalization and information retrieval (IR) as well as on automated machine learning (AutoML), meta-learning and algorithm selection. Domains we are particularly interested in include smart places, eHealth, manufacturing (industry 4.0), mobility, visual computing, and digital libraries. We founded or maintain, among others, LensKit-Auto, Darwin & Goliath, Mr. DLib, and Docear, each with thousand of users; we contributed to TensorFlow, JabRef and others; and we developed the first prototypes of automated recommender systems (AutoSurprise and Auto-CaseRec) and Federated Meta Learning (FMLearn Server and Client).