Nitzan is a Technology Executive driving innovation and outsized business growth in online travel, financial services, media, and healthcare, through cloud-native data strategies and real-time ML/AI products at scale. His areas of focus include enterprise cloud-native platforms, hyper-personalization in web and mobile, alternative data, fraud detection, NLP and computer vision for automation.
eBay chief AI officer details how the shopping site's computer vision is driving customer satisfaction with image-based search.
The adage that data is king is true, probably nowhere more than in training CD models for item-matching. And for us, this was compounded at the time [by] the fact that we don’t control all the ways in which our sellers photograph their items. Hardware also posed issues in the first years, and the company had to find creative solutions. First, we did our training separately. We trained the models on the public cloud, where we could access [graphic processing units]. Then we did the inference and deployment locally. We also set up a series of what were essentially stateless systems, holding the entire index in memory.