Help customers return to the right pack, not just the next promotion.
When a regular buying pattern changes, compare a relevant offer, a service check and no action before contacting the customer.
Customer value is lost because actions are broad, late, conflicting or not measured against doing nothing.
Usually owned by Chief Commercial Officer
Runs end to end, configured for your organisation and market.
Verified work email required.
Move the inputs and the checks, the ranking and the decision are computed again. Sample records, computed in your browser.
A pilot prepares this decision on your data, systems and policy, with the comparison agreed first.
Regular data buyer: no pack for 6 weeks, 41% of the last one used, contacted 25 days ago.
Every check permits it, so the ranking chose the option worth the most to both sides.
Computed for a generic sample market. Move the inputs and watch it change
Sample records.
The demonstration below runs on a generic sample. Tell us your market and it will use figures and a name that fit.
Configure a demonstrationA customer who bought a data pack every month for a year has bought nothing for six weeks. Nothing has broken and nobody has complained.
A regular buying pattern stops, and the gap passes the point where it stops looking like a pause.
Recent usage, recharge and contact history are read before anything is proposed, so a customer who has gone quiet and a customer with a service fault are told apart.
A right-sized pack, a service check and no action are ranked together, and consent, contact frequency, fair value, margin and an open case can each refuse.
Every run keeps its inputs, checks and outcome, and a pilot compares treated customers against a holdout before any value is claimed.
The records below are a sample and the figures are generic. Say which market you are in and they will fit it. Move any input and the checks, the ranking and the decision are computed again.
Customer · ILL-NEU-0001 · 36 months · Regular data buyer
Unchanged, as the sample records have it.
Their usage fits a smaller pack than the one they were buying. A fair-value match is more likely to be taken than a discount on the pack they already stopped buying.
Small weekly pack · 190 · 1.5 GB for 7 days · 72 margin after the incentive
Every check permits it, so the ranking chose the option worth the most to both sides.
| Check | Result | Why |
|---|---|---|
| Marketing consentConsent and preference system | Permits | Consented on SMS. |
| Contact frequencyCampaign management system | Permits | Last contacted 25 days ago; the floor is 14. |
| Fair valueProduct catalogue and pricing | Permits | Using 41% of the pack they were buying, so a smaller pack is the fair match. |
| Margin floorCommercial finance | Permits | 72 remains on Small weekly pack after the incentive. |
| Open service caseCare and service management | Permits | No unresolved case on this account. |
The open-case check reads this market’s own records rather than a field on the customer, so it is not one of the controls.
A smaller weekly pack matching your recent usage is available. Reply 1 to accept.
Reply 0 to stop receiving these offers.
English · SMSUsage or care data has not refreshed inside the window the decision requires, so eligibility cannot be established.
No market has been configured, so usage and care data have no agreed freshness window. Eligibility cannot be established.
Remedy. No action is taken on stale context. The decision returns no-action with the source and its age named.
Handed to Data operations, with the source and freshness recorded.
Sample records, computed in your browser. Record set FX-NEUTRAL v3, scenario SCN-PACK-DROPOUT. See the whole journey, with the receipt and the evidence record
Hypothesis
A customer who is drifting away is cheaper to keep than to replace, and an offer sent over an unresolved fault costs more than it earns.
Desired result: Incremental revenue or retention; lower contact waste; improved conversion with margin guardrails
Modelled not observed
A run on the sample records shows the decision, the checks it passed and the receipt the responsible system would return. No incremental value is modelled on this page.
Ingest → qualify → score → apply limits/consent → assign control → execute approved action → capture delivery and business outcome → monitor/retrain
Observed
Nothing yet. Measurement begins in a pilot’s validate stage, on your systems, against a comparison agreed first.
Randomised holdout where feasible; intent-to-treat primary view; pre-declared denominator; guardrails for complaints, margin and opt-out
Measured on: Eligible population; treatment rate; conversion; incremental revenue; ARPU; churn; contact rate; margin; opt-out; decision latency
The result wanted.
Incremental revenue or retention; lower contact waste; improved conversion with margin guardrails
The mechanism that could produce it.
Ingest → qualify → score → apply limits/consent → assign control → execute approved action → capture delivery and business outcome → monitor/retrain
The records kept to show it.
Decision log; eligibility snapshot; price/order response; delivery receipt; control assignment; revenue/outcome ledger
The cost, and the ways it can go wrong.
Costs: Setup fee + annual product subscription; optional managed execution fee; optional verified-outcome fee with agreed baseline
If it fails: Fail closed on eligibility/consent/price; queue retryable events; do not duplicate orders; route exception to campaign operations
The measure that shows it helped.
Randomised holdout where feasible; intent-to-treat primary view; pre-declared denominator; guardrails for complaints, margin and opt-out
Measured on: Eligible population; treatment rate; conversion; incremental revenue; ARPU; churn; contact rate; margin; opt-out; decision latency
A saved run keeps the decision and its receipt: what was decided, which checks refused, and what the responsible system returned. It does not show incremental value. That needs the comparison above, over an agreed period, against a baseline finance has accepted.
The business side
Four questions an evaluation asks in a different order every time. Every field is the workbook’s own, unedited.
What would we need from your systems, and how much history?
8-12 weeks of customer, usage, revenue, product, contact and outcome history; stable customer key; one executable channel
How is the action chosen, and what stops it?
Fail closed on eligibility/consent/price; queue retryable events; do not duplicate orders; route exception to campaign operations
What does it connect to, and what stays authoritative?
Charging, billing, catalogue, consent and order systems remain authoritative; HeuriTel decides only within approved policy.
What is kept, and how would a claim be tested?
Randomised holdout where feasible; intent-to-treat primary view; pre-declared denominator; guardrails for complaints, margin and opt-out
22 in this product
Identify eligible records for cvm, choose from approved actions including no action, execute through the system of record, and measure the agreed business outcome.
/d/HT-0001Identify eligible records for customer 360, choose from approved actions including no action, execute through the system of record, and measure the agreed business outcome.
/d/HT-0002Identify eligible records for customer segmentation, choose from approved actions including no action, execute through the system of record, and measure the agreed business outcome.
/d/HT-0003Identify eligible records for micro-segmentation, choose from approved actions including no action, execute through the system of record, and measure the agreed business outcome.
/d/HT-0004Identify eligible records for customer lifecycle, choose from approved actions including no action, execute through the system of record, and measure the agreed business outcome.
/d/HT-0005Rank eligible commercial or service actions for each customer, including do nothing, under consent, contact, margin and product rules.
/d/HT-0006Rank only offers the customer can buy and the operator can fulfil, then capture order, margin and incremental conversion.
/d/HT-0007Identify customers with a defined near-term churn risk, select only economically justified retention actions, and measure incremental saves against a holdout.
/d/HT-0008Identify eligible records for retention, choose from approved actions including no action, execute through the system of record, and measure the agreed business outcome.
/d/HT-0009Identify eligible records for win-back, choose from approved actions including no action, execute through the system of record, and measure the agreed business outcome.
/d/HT-0010Identify eligible records for dormant customer reactivation, choose from approved actions including no action, execute through the system of record, and measure the agreed business outcome.
/d/HT-0011Identify eligible records for customer lifetime value, choose from approved actions including no action, execute through the system of record, and measure the agreed business outcome.
/d/HT-0012Identify eligible records for arpu growth, choose from approved actions including no action, execute through the system of record, and measure the agreed business outcome.
/d/HT-0013Identify eligible records for upsell, choose from approved actions including no action, execute through the system of record, and measure the agreed business outcome.
/d/HT-0014Identify eligible records for cross-sell, choose from approved actions including no action, execute through the system of record, and measure the agreed business outcome.
/d/HT-0015Identify eligible records for prepaid-to-postpaid migration, choose from approved actions including no action, execute through the system of record, and measure the agreed business outcome.
/d/HT-0016Identify eligible records for high-value customer management, choose from approved actions including no action, execute through the system of record, and measure the agreed business outcome.
/d/HT-0017Identify eligible records for new customer onboarding, choose from approved actions including no action, execute through the system of record, and measure the agreed business outcome.
/d/HT-0018Identify eligible records for usage growth, choose from approved actions including no action, execute through the system of record, and measure the agreed business outcome.
/d/HT-0019Identify eligible records for share-of-wallet growth, choose from approved actions including no action, execute through the system of record, and measure the agreed business outcome.
/d/HT-0020Use customer affordability, usage, renewal and margin data to improve recharge-to-usage conversion while controlling cannibalisation and measuring incremental value.
/d/HT-0021Identify eligible records for customer value migration, choose from approved actions including no action, execute through the system of record, and measure the agreed business outcome.
/d/HT-002212-16 weeks to pilot; 2-4 additional weeks per market after reusable interfaces exist. A team of 8 roles, named in the record rather than promised.
One use case, one value unit and a denominator finance has agreed to. Without these there is nothing a later result can be compared against.
The attributes mapped from your systems, and the decision and outcome interfaces working in both directions.
Eligibility agreed, a dry run with nothing sent, then a controlled pilot with a holdout that is actually respected.
The live loop: decide, check, execute through your systems, capture what came back, and measure against the control.
Who does it. 1 telecom product lead · 1 CVM specialist · 1 data engineer · 1 ML engineer · 1 integration developer · 0.5 QA · 0.5 DevSecOps · 1 deployment coordinator
Readiness is assessed per client: nothing is offered as pilot-ready until your data, your integration and your authority have been checked.
Needs client data and integration review
The client’s data and integration position.Target product definition
What exists as running software.Not audited
Whether this product shows the entry anywhere.Not assessed
Where a named client has reached.22 definitions sit under Customer Growth & CVM. The two links that matter first are the journey this page has been running a piece of, and the rest of the family it belongs to.