Snowflake readies Amazon retail data for demand forecasting

Cloud data warehouse darling Snowflake has been investing a lot in its data ecosystem. Yesterday, the company made a broad announcement around the launch of its Retail Data Cloud, which integrates the core Snowflake platform with partner-delivered solutions and industry-specific datasets. Today, the company is announcing an important initiative within that rollout, which it shared exclusively with VentureBeat: it’s partnering with Amazon Web Services (AWS) to bring Amazon.com sales channel data directly into customers’ Snowflake data warehouse instances.

Data for sales intelligence

This is a data-driven age for retail, a phenomenon accelerated by the pandemic and the twists and turns COVID has created in buyer preferences and purchasing patterns. The provision of the Amazon.com data is intended to help retail and CPG (consumer packaged goods) customers not only monitor Amazon.com Vendor Central PO data, but also leverage Amazon Forecast functionality within their Snowflake environments.

The offering enables sophisticated demand forecasting and helps manage upstream logistics, including lead times for manufacturing and delivery. The companies also explain the data enables customers to track product weight or dimension changes; reduce on-time in-full (OTIF) penalties/improve OTIF metrics; and ensure high-sales SKUs (items) stay in-stock. Such analyses can help companies mitigate the impact of supply chain irregularities and improve the all-important customer experience.

Analysis, ready

As the folks from Snowflake and AWS tell the story, this initiative is about way more than raw data feeds. Rather, it provides a collection of high-value data sets that have already gone through significant data integration processes to help customers avoid pulling and blending data from multiple accounts. 

The data also goes through significant data engineering processes that make it analysis-ready right out of the gate. The result: retail brands and CPG businesses get purchase order history and updates, down to the line item level, as well as granular product catalog metadata, providing the ability to perform probabilistic PO forecasting at the ASIN (Amazon Standard Identification Number) or fulfillment center level.

This all goes beyond abstract concepts expressed in a press release. In fact, in an exclusive briefing with VentureBeat, Rosemary Hua, global head of Retail & CPG at Snowflake, and Justin Honaman, head of Worldwide Consumer Packaged Goods at AWS, showed how BI tools could be used directly against the Amazon retail data. Creating visualizations of demand against current stock levels, or top-selling product forecast shortage by geographical region (partially shown in the figure at the top of this post), become fairly straightforward, right from a major BI tool (Tableau, in the case of screenshots shown to us).

If you’re interested in the mechanics of all this, they’re remarkably straightforward. Data is inserted directly into customer Amazon S3 buckets. From there, Snowflake can detect the presence of the data, determine its schema and automatically refresh the latter as necessary. Customers then have the ability to use and analyze the data in a standalone fashion or join it to data from other, third-party sources in the Snowflake Data Marketplace.

Search criteria

When it comes to looking at the cloud data warehouse market, it’s fairly easy to focus on which competitor has the most born-in-the-cloud solution, the best enterprise-class performance and pedigree, or the smoothest combination of the two. But maybe the contest between those sets of criteria misses the point.

The technology, including its performance and features, is critical, of course. But so too is the partner ecosystem and, yes, the data. Enterprise application companies like SAP and Oracle appreciate that, offering analytics in the context of transactional data. Snowflake seems to see that value too. Perhaps, as an independent cloud data warehouse provider, emphasizing its partner and data ecosystem is Snowflake’s biggest innovation. If we look past the core platforms themselves, and take seriously the notion of what a “data cloud” really means, then maybe the metrics and dimensions of the cloud data warehouse market start to change.