How BMW Group detects cost anomalies across 14,000 cloud accounts
BMW Group operates CLEA, a FinOps platform monitoring more than 14,000 cloud accounts. This post shows how BMW added automated daily cost anomaly detection, moving from reactive dashboards to proactive alerts using Prophet forecasting, AWS Step Functions, and a serverless pipeline that processes every account for about $50 per month.
BMW Group's Cloud Efficiency Analytics (CLEA) system detects cost anomalies across 14,000 cloud accounts. The FinOps platform, built on AWS with support from partner Data Reply, monitors and analyzes spending patterns. CLEA ingests billing data from AWS Cost and Usage Reports (CUR) and other provider exports, aggregating the raw data into daily cost per account per service.
The system employs a forecasting baseline using Meta's Prophet library, trained on 365 days of historical data for each account-service pair. It then compares actual spend to the expected spend, flagging deviations that exceed a 40% threshold. The serverless architecture processes the data daily, costing around $50 per month in compute.
Written by urgent.news from AWS Machine Learning's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
