lead_processing · workflow
Building a machine learning pipeline with DBT and BigQuery ML to predict user applications
Building a proper data pipeline for feature engineering, model training, and predictions is complicated, and moving data out of the database adds operational overhead.
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 · Load user event data
User event data is uploaded to BigQuery as a mixpanel dataset for use in the ML pipeline.
Tools used
BigQuery MLDBTdbt_ml
Outcome
A DBT and BigQuery ML pipeline was built that predicts which users are most likely to apply to a program, enabling the sales team to target top leads and identify which site events drive applications.
Results
Volume.93
Grounding & classification
Source type: technical build writeup
14 fields verified against source quotes.
predictive analyticsmetric backedsource backedtools describedworkflow describededucationconversion increasetechnical build writeuplead processingmarketing opsextract classify route