compliance_monitoring · workflow

Monzo's machine learning stack: principles, platform architecture, and tools

Monzo needed a scalable machine learning platform that let ML practitioners deploy models end-to-end without backend engineer handoffs, remained flexible across frameworks and model types, and reused existing infrastructure rather than building an isolated ML-specific stack.

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 · Prototype in notebooks
Ideas are explored in Google Colab notebooks to gauge viability before being moved into the codebase.
Tools used
Google ColabGitHubcookiecutterBigQueryGoogle Cloud StorageGoogle Container RegistrydbtAirflowGoogle Pub SubNSQCassandraGrafanaLookerscikit-learnXGBoostLightGBMPyTorchtransformersskorchGensim
Outcome

The platform lets the ML team spend little to no time managing infrastructure. A uniform approach means engineers can move between ML systems easily, and upgrades are applied once and benefit everyone.

Results
Time savedlittle to no time managing infrastructure
Source

https://monzo.com/blog/2022/04/26/monzos-machine-learning-stack

How we source this →

Grounding & classification
Source type: technical build writeup
32 fields verified against source quotes, 2 dropped as unverifiable.
fraud detectionpredictive analyticsnamed customerproduction runtime claimedtools describedworkflow describedbankingemployee productivitytechnical build writeupcompliance monitoringfinance opsmonitor detect alert