Mirakl deployed AI to add products to catalogs
Mirakl uses fine-tuned and open models running on GPUs and inference software from NVIDIA. According to NVIDIA, it has added over 70 million products this way and reduced the time required to onboard seller catalogs to less than two hours.
Mirakl used fine-tuned and open models to add sellers' products to catalogs. According to a press release from NVIDIA, the models run on GPUs and inference software from NVIDIA.
According to NVIDIA, more than 70 million products were added this way, and the time required to onboard seller catalogs was reduced to less than two hours. These results come from the technology supplier; the press release does not state the original processing time or the size of the catalogs to which the reported time applies.
Why it matters
For companies processing seller catalogs, this case provides a basis for assessing a similar AI deployment. It reports a specific processing volume and the time achieved, but without the original onboarding time, the degree of speedup cannot be quantified.
Relevant practical impact
What this means
For a business
The impact concerns the process of onboarding seller catalogs. According to NVIDIA, Mirakl reduced the time required to less than two hours using fine-tuned and open models.
Processes More business impacts →Check the original
Event sources
only one source so far · 1 publisher, 0 independent. We count feeds from the same owner only once.