Analyze GA4 BigQuery data with ads, orders, and CRM
If your team already uses GA4 BigQuery Export, you can analyze event, acquisition, and ecommerce data alongside ad accounts, orders, and CRM outcomes.
Platform conversions don’t tell you what the business earned
Ad platforms report clicks, conversions, conversion value, and ROAS. Refunds, product margins, first purchases, and repeat orders live somewhere else: your order system, CRM, or warehouse. A campaign can look efficient in Ads Manager and still underperform on settled revenue or profit.
The answer isn’t always another dashboard. If GA4 events and first-party data already live in BigQuery, the more useful step is to bring them into the same analysis as your ad accounts. Pango Neuro connects selected BigQuery datasets to Claude or ChatGPT through MCP, where marketers can ask questions in plain language while the AI inspects the available tables and schemas.
The connection is read-only and limited to datasets you choose
Pango Neuro doesn’t copy your entire warehouse into its own database. You authenticate with Google, select the datasets the connection may access, and add optional notes about table and field meanings. The BigQuery tools can list tables, inspect schemas, and run SELECT queries. The server rejects writes, updates, and deletes.
| BigQuery data | Question to ask with ad data | Decision it supports |
|---|---|---|
| Orders, payments, and refunds | How does channel ROAS change when we use net revenue after refunds? | Separate campaigns that drive settled revenue from campaigns that only look strong in-platform. |
| Customer and CRM records | How do CAC and revenue differ for new and returning customers by channel? | Set different expectations for acquisition and retention spend. |
| Products and margins | Which campaigns generate the most contribution margin after ad spend? | Prioritize profitable product groups instead of gross revenue alone. |
| Leads and sales stages | Which campaigns produce qualified opportunities and closed deals? | Evaluate lead generation on sales outcomes, not form fills alone. |
Already using GA4 BigQuery Export? Connect the existing dataset
GA4 BigQuery Export creates an `analytics_<property_id>` dataset with daily `events_YYYYMMDD` tables. Pango Neuro does not create the GA4-to-BigQuery link or export historical data for you. An existing export must be available, and data from before the export was enabled is not automatically backfilled.
| GA4 BigQuery data | Marketing question | Useful data to add |
|---|---|---|
| page_view, view_item, add_to_cart, and purchase events | Which landing pages and acquisition campaigns lose the most users before purchase? | Ad spend and campaign or creative performance |
| Source, medium, campaign, and session acquisition fields | Which acquired sessions continue from ad click to meaningful behavior and purchase? | Google Ads, Meta, and other channel results |
| ecommerce.transaction_id and items | How closely do GA4 purchases match paid, canceled, and refunded orders? | Order ID, product ID, net revenue, and margin |
| An explicitly collected user_id | How do journeys and revenue differ between new and returning customers? | A privacy-minimized customer or CRM view |
A reliable analysis starts with shared keys and definitions
Connecting BigQuery doesn’t automatically make every join correct. Row-level reconciliation requires a shared identifier such as `transaction_id` or an explicitly collected `user_id`. Comparing date, source, medium, and campaign can show aggregate trends, but it does not prove which campaign caused an individual order. The team also needs to define revenue: payment captured, order completed, or net of refunds. The AI can inspect the schema and write a query, but it shouldn’t invent your business definitions.
- Align the date range, currency, and time zone across the ad account and BigQuery.
- Confirm whether GA4 and order or customer tables contain a real shared identifier.
- Choose the revenue definition the team will use for decisions.
- Validate a short date range against a known report before expanding the analysis.
Choose the GA4 dataset and ask your first question in four steps
- Confirm the GA4 `analytics_<property_id>` dataset and any order or CRM datasets you want to compare.
- In Pango Neuro service integrations, choose BigQuery and sign in with the Google account that can access the data.
- Select the allowed datasets, set scan limits, and add notes for important tables or status codes.
- Validate the connection with a question you can check in GA4, such as event and purchase counts for the last seven completed days.
Queries above the per-query or daily scan limit are blocked before execution. BigQuery charges go to your Google Cloud project separately from the Pango Neuro subscription. Select only needed columns and date tables; LIMIT can reduce returned rows without reducing bytes scanned on a non-clustered table.
Questions to try on the first day
BigQuery integration is useful for more than hiding SQL. It gives marketing, analytics, and finance teams a repeatable way to use the same definitions across ad spend, orders, customers, and sales outcomes. Start with one short, verifiable net-revenue analysis, then expand the workflows your team can trust.
Related posts
Google Ads MCP: A marketer’s guide to analysis, reporting, and action
Learn what a Google Ads MCP server does between Claude and the Google Ads API, which workflows matter to marketers, and how to choose and use one safely.
How to fill ad reports straight into Google Sheets
A guide for teams that run their client-facing and internal reports in Google Sheets: how to point Neuro at a URL, tab, and range in chat and let AI fill in the data for you.
The order an AI agent should read an ad account in
Auditing an ad account isn't about staring at ROAS alone. It's about working through goals, structure, budget, conversion quality, and creative signals in order.
A Neuro security guide for teams nervous about connecting their ad accounts
What we can share publicly: whether Neuro ever holds your passwords when you connect an ad account, how far the permission scope goes, whether AI uses your data for training, and how each advertiser’s data stays isolated.
Sources
- Google Analytics: BigQuery Export schema
Google’s reference for GA4 export datasets, daily and intraday event tables, and acquisition, user, and ecommerce fields.
- Google Analytics: Compare Analytics reports and BigQuery export
Google’s guidance on differences caused by reporting identity, time zone, excluded streams, and excluded events.
- Google Analytics: Set up BigQuery Export
Google’s setup guide for linking a GA4 property to BigQuery, export types, limits, and when data starts flowing.
- Google Cloud: BigQuery IAM roles and permissions
Google’s reference for BigQuery Data Viewer, BigQuery Job User, and the permissions required to read data and run query jobs.
- Google Cloud: Estimate and control costs
Google’s guidance on dry runs, maximum bytes billed, daily query quotas, partition filters, and column selection.
- Google Cloud: BigQuery pricing
Google’s explanation of on-demand query pricing by bytes processed and the available cost-control mechanisms.