supply_chain · ecommerce · workflow

Cainz cuts sales data preprocessing time to 50 minutes across 209 stores with Vertex AI

Cainz's demand forecasting relied on experienced distributors and a fixed-order-quantity system using moving averages that could not accurately predict seasonal products or short-term sales trends. As the company planned to expand AI coverage across hundreds of stores, preprocessing data from even a handful of stores took three hours, making same-day completion at full scale impossible.

How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Weekly sales data trigger
The demand prediction model is trained once a week using sales data.
Tools used
Vertex AIVertex AI ForecastVertex Explainable AICloud Run jobsTAPBigQueryCloud StorageWorkflows
Outcome

Cainz deployed its AI-powered demand forecasting solution across 209 stores, reducing data preprocessing time to 50 minutes regardless of the number of stores, and enabling more accurate stock replenishment predictions.

What failed first

Cainz initially used a third-party solution to train the demand model, but as the scope of demand prediction expanded, the solution showed its limitations and was replaced with Vertex AI Forecast.

Results
Time saved50 minutes
Volume209 stores
Running sinceJune 2022
Source

https://cloud.google.com/customers/cainz

How we source this →

Grounding & classification
Source type: vendor customer story
28 fields verified against source quotes.
forecastingpredictive analyticsproduct catalogfailure mode describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedretailaccuracy improvementcycle time reductionthroughput increasevendor customer storyback office opssupply chaindata sync enrichment