Baltic CVM LabCompetitive pricing and retention decision intelligence · Latvia
Baltic CVM Lab
Competitive pricing index and retention decision layer · Latvia · public price lists and a synthetic base · no operator data
30
Offers tracked
3 operators, published prices
16
Personas
priceable baskets
6
Ahead
of 6 priced
9
Unserved
no qualifying offer
35
Tests green
one per shipped defect
1.2%
Base churn
monthly, in published band
What this is. A working competitive-pricing index for the
Latvian mobile market built from the operators' own published price lists, plus a decision
layer that tests whether retention offers are economically viable. It is a demonstration of
method — a reference implementation of the pilot concept, not a product. No operator
data of any kind is used.
Build state against the concept
The concept specifies nine views. 1.5 of 9 exist in
some form. This is shown rather than hidden — a menu that promises screens which do not exist
is worse than a short menu.
Two adapters compared under one policy. No live swap control.
partial
12.8
Governance
AI Act evidence pack, searchable decision log, fairness monitors.
not built
12.9
MCP surface
Natural-language querying of the semantic layer.
not built
Proof-of-concept modules
Module
Note
Status
A · External signal
3 operators in 1 market. Concept scope is 9 operators across 3 markets, with movement detection.
partial
B · Simulated estate
Calibrated and CI-gated — but emitted as ONE CLEAN TABLE. The concept explicitly warns that this assumes away the real problem: the estate should arrive as separate systems with conflicting definitions.
partial
C · Vendor adapter
Two interchangeable adapters, one deliberately worse.
built
D · Sovereign core
Policy engine, score interception and uplift built. Semantic layer, evidence store and knowledge base are not.
partial
E · Surfaces
3 of 9 concept views, plus overview and method pages.
partial
Current position — Latvia
Persona
Reference operator
Best competitor
Position
Value Seeker
€16.99
lmt €30.98
ahead €13.99
Digital Native
€30.89
lmt €30.98
ahead €0.09
Cross-border Commuter
€30.89
lmt €30.98
ahead €0.09
Voice-first Senior
€16.99
lmt €30.98
ahead €13.99
Student / Youth
€30.89
lmt €30.98
ahead €0.09
Prepaid Occasional
€16.99
lmt €30.98
ahead €13.99
Compared on standard rates, not promotional headlines.
9 personas are unserved by every operator — multi-line family baskets, which no
extractor captures yet. Reported as a finding rather than filled in.
Three findings worth the click
Advertised prices rank differently from standard rates. Tele2's
unlimited plan promotes below its own 25 GB plan, so an index built on headlines reports a
position that reverses when the promotion ends.
The conventional retention offer cannot break even at any targeting quality.
18% × 6 months needs ~17pp of uplift; at 1.2% monthly churn the ceiling is ~5pp. An earlier
claim of a €44k gain from better targeting was withdrawn after calibration.
Semantic layer and lineage — the concept's §12.6, which it calls the
most strategically important screen, does not exist. Feature definitions live in code and YAML
but are not surfaced with owner, lawful basis or quality SLO.
The estate is one clean table. The concept explicitly warns against
this: a proof of concept with a single tidy table assumes away the reconciliation problem that
the semantic plane exists to solve.
No evidence store. Decisions are produced but not persisted
append-only, so the decision log — the asset the concept says cannot be regenerated once
lost — does not yet exist.
Persona weights are uncalibrated. Informed estimates, not measured
against SPRK, RRT or TTJA statistics.