Follow Datanami:
January 21, 2022

Google Cloud Announces Vertex AI Tool for Demand Forecasting

In a blog post, Google Cloud has announced Vertex AI Forecast, a machine learning tool for advancing demand forecasting. The forecasting tool is an extension of Vertex AI, the managed machine learning platform aimed at helping enterprise customers deploy and maintain AI models that was announced last spring at Google I/O 2021. Google says that Vertex AI Forecast, which is available now, can generate accurate demand forecasts within just hours and is already being integrated by major retail and supply chain partners.

“For retailers, supply chain, and consumer goods organizations, accurate demand forecasting has always been a key driver of efficient business planning, inventory management, streamlined logistics, and customer satisfaction,” wrote Craig Wiley, director of product management for cloud AI and industry solutions at Google, in the blog post. “Accurate forecasting is critical to ensure that the right products, in the right volumes, are delivered to the right locations. … Yet, inventory management is only one of the applications among many that demand forecasting can support—retailers need to also staff their stores and their support centers for busy periods, plan promotions and evaluate different factors that can impact store or online traffic.”

Vertex AI Forecast, made to address this use case, is the latest brainchild from Google Brain, a machine learning team that operates under Google AI. (Google Brain tech is also at work in products like TensorFlow, Google Photos, and Google Translate.) Google says that the tool can “ingest datasets of up to 100 million rows covering years of historical data for many thousands of product lines from BigQuery or CSV files,” after which the data is automatically processed and matched with fitting model architectures. The best architectures are then packaged into a single model that Google says is “easy to manage, even without advanced data science expertise” and which can be generated in just two hours with no tuning.

Vertex AI Forecast accommodates up to 1,000 distinct demand driver variables (like color or brand) and allows users to set budgets and analyze forecast results at levels from the item to the region. Google says the tool is already in use by companies like o9 Solutions, Quantiphi, and Lowe’s.

“At Lowe’s, our stores and operations stretch across the United States, so it’s critical that we have highly accurate SKU-level forecasts to make decisions about allocating inventory to specific stores and replenishing items in high demand,” said Amaresh Siva, senior vice president for innovation, data, and supply chain technology at Lowe’s. “Using Vertex AI Forecast, Lowe’s has been able to create accurate hierarchical models that balance between SKU and store-level forecasts. These models take into account our store-level, SKU-level, and region-level inventory, promotions data and multiple other signals, and are yielding more accurate forecasts.”

Related Items

Google Cloud Overhauls AI with Vertex Launch

Google Cloud Widens Its Big Data Reach at Next ’21

Google Cloud Attacks Supply Chain Crisis with Digital Twin