Multivariate time series forecasting allows BigQuery users to use external covariate along with target metric for forecasting.
Recently, I published a blog on whether self-service BI is attainable, and spoiler alert: it certainly is. Of course, anything of value usually does require a bit of planning, collaboration, and effort. After the article was published, I began having conversations with technical leaders, analysts, and analytics engineers, and the topic of data modeling for self-service analytics came up repeatedly.
The Chief Data Officer is arguably one of the most important roles at a company, particularly those that aspire to be data-driven. CDO appointments and the elevation of data leaders have accelerated in recent years, and the role has morphed as perceptions of data have evolved. Responsibilities span strategy and execution, people and processes, and the technology needed to deliver on the promise of data.
Google Cloud customers who want app-level encryption in hybrid cloud data warehouses can encrypt and decrypt that data outside BigQuery. Here’s how to do that securely.
Organizations have been focused on enhancing customer experiences to enable quicker responses to services and to provide localized behavior for many years now. However, with the Internet of Things (IoT), Smart Cities, Gaming technologies and Self-Driving Cars going more mainstream, there is an even greater need for organizations to react faster to customer behavior and bring solutions closer to the customers.
Deploying models is becoming easier every day, especially thanks to excellent tutorials like Transformers-Deploy. It talks about how to convert and optimize a Hugging face model and deploy it on the Nvidia Triton inference server. Nvidia Triton is an exceptionally fast and solid tool and should be very high on the list when searching for ways to deploy a model. If you haven’t read the blogpost yet, do it now first, I will be referencing it quite a bit in this blogpost.
