Until now we have mainly talked about forecasting regular products that have been on the shelf for quite some time. But what about products that have been very recently launched ?
The end-of-year period is ever more strategic and competitive for brands selling their products on Amazon. Both Black Friday and the holiday season are catalysts for sales, increasing buying opportunities for end consumers, but also galvanising competition between brands: on price, product quality and visibility through advertising both on and off Amazon. It’s essential today to take advantage of all the tools and solutions offered by Amazon. This article highlights our 10 golden rules for harnessing the full power of the American company's advertising ecosystem.
To the casual observer, the motor industry might seem in good health, with electric and hybrid vehicles increasingly appearing on our streets and driverless cars becoming a reality, not to mention people preferring the safety of their car over public transport following the coronavirus pandemic. But this surface view belies an industry in flux, facing change from several directions.
A guide to being aware of the risks you are exposed to and a few tips to protect against them.
Nowadays, advertising saturation on all channels causes the message we want to transmit to be too repetitive and does not inspire interest for the user. In this sense, the option of generating coherent Storytelling for the user can be a complicated task. If we have a brief where video actions and storytelling are proposed, I think that the YouTube Ad sequence could be an option to value. Using this type of strategy, we have seen increases in frequency up to 2.4x and Brand Awareness up to 4x through YouTube Brand lift measurements.
For over a year and a half, organizations have undertaken a continuous cycle of innovation and adaptation to meet the changing environment as the pandemic continues to play out. Ghadi Hobeika, CEO of Artefact in the US, provides an overview of seven learnings from the pandemic for the long-term.
This article is the third part of a series in which we go through the process of logging models using Mlflow, serving them on Kubernetes engine and finally scaling them up according to our application needs. Although this article could be used independently to test any API response, we recommend reading our two previous articles (part1 and part2) on how to deploy a tracking instance and serve a model as an API with Mlflow. In the following, we will be interested in the scalability issue and address it with few experiments to understand k8s cluster behavior and give recommendations on how to handle high loads.
25 October 2021 This article is the second part of a series in which we go through the process of logging models using Mlflow, serving them as an API endpoint, and finally scaling them up according to our application needs. We encourage you to read our previous article in which we show how to deploy a tracking instance on k8s and check the hands-on prerequisites (secrets, environment variables…) as we will continue to build upon them here. In the following, we show how to serve a machine learning model that is already registered in Mlflow and expose it as an API endpoint on k8s.
22 October 2021 MLflow is a commonly used tool for machine learning experiments tracking, models versioning, and serving. In our first article of the series “Serving ML models at scale”, we explain how to deploy the tracking instance on Kubernetes and use it to log experiments and store models.
