ARIMA_PLUS and ML.DETECT_ANOMALIES are built into BigQuery, so the setup is straightforward — the concepts underneath are not. The four ideas to understand before you turn anomaly detection on.
In this post, a simple query that answers: Which search terms predict a purchase, even when that purchase happens days later in a different session?
Try to find that via the GA4 interface…
You finally got your GA4 data in BigQuery. You write your first query. And then you meet UNNEST. If you’ve worked
Cart abandonment is one of those things everyone knows is a problem and nobody fully understands. The usual dashboard tells you the rate. It doesn’t tell you why.
This query gives you the top “last 3 pages before abandoning a cart” for extra insight
Here’s an article on the ga4_transactions table, with a query that solves an actual use case: which product categories make customers loyal?
Our good friend (and now BFF) Mehdi Oudjida is a Looker Studio expert and created a Looker Studio Template for the Sessions demo table!
