Forecasts that are later checked against fact
Valkiria forecasts impressions, clicks, conversions, revenue, budget, audience, churn and growth from your own history alone, and stores each one with its confidence and source references. When the real numbers arrive, the forecast is compared with them and scored for accuracy.
01What hurts
Why a forecast usually costs nothing
The forecast lives in someone's head
"Last month was this, so this month will be about the same" — and next month's budget gets planned on intuition rather than on data.
Nobody checks the AI forecast
The model states a number with confidence, and a month later nobody comes back to see whether it held. The error is never found, and the same model predicts again.
The number has no source
A tidy figure with no note of which data produced it, or what was missing from that data, can be neither challenged nor defended in front of a client.
Scroll to see it work
Predictive analytics in four moves
- 01Scattered
Without Predictive analytics, this work is spread across spreadsheets and tabs.
- 02Connected
Predictive analytics reads the accounts and data you have already connected.
- 03Found
It highlights what matters now, with the evidence behind it.
- 04Approved
You decide what happens next: what applies on its own and what waits for approval.
02How it works
How a forecast is built and verified
- 01
Feed it the history
The module hands the model your accumulated performance. Its instructions forbid going beyond that data and require listing sources, assumptions and any missing evidence.
- 02
Generate the forecast
One button builds forecasts for the period — 30 days by default. Each record is stored with its type, category, confidence and an unverified-estimate status.
- 03
Check it against fact
When the period closes, the actual values and an accuracy score are attached, so you see which predictions deserve trust and which do not.
03What you get
What predictive analytics gives you
Eight forecast types
Performance, budget, audience, revenue, CTR, conversions, churn and growth, filtered by category in a single list.
01A confidence on every record
A forecast with no confidence is labelled "needs evidence", and how confidence moves over time is drawn on its own chart.
02Back-testing built in
Forecast and actual sit side by side, accuracy is scored as a percentage, and the average across all forecasts tells you what the model is worth.
03A factuality badge per card
The status shows whether sources back the forecast: an unverified estimate can never be applied automatically.
04A forecast you can budget with
Expected impressions, clicks and conversions for the next 30 days come as a chart you can put behind a spend plan.
05Your choice of AI provider
The Ollama → z.ai → OpenAI → Anthropic → Qwen chain is configured per install, so nothing is hard-wired to one vendor.
0604In numbers
- 8
- forecast types, from CTR to churn
- 30
- days — the default forecast horizon
- 0
- forecasts applied without a human
Who gets what
What each type of client takes away
What you connect
- Ad accounts
- Analytics
- Website
- Bank & invoices
What Valkiria does
- 01Collect spend and results
- 02Find leaks and gaps
- 03Propose next steps
What you get
- Action plan
- Owner report
- Spend control
See every ad budget and what it returns, without opening five dashboards
Google, Meta, TikTok and the rest in one view, in your currency, with results next to costs.
Findings turn into a prioritised list of next steps with the evidence behind each one.
New campaigns are created paused. Edits to live campaigns stay off until you switch them on for an account; deletions and new spend always wait for approval.
Modules that do the work
05FAQ
Questions about ad forecasting
06See also
All modulesStart now
Build a forecast you can verify
Forecasts are built from your data, labelled as estimates and never applied on their own. You can check the accuracy after the very first cycle.