Manaz Afzal
Telecommunications

Plan upgrade offers for the households heading past their allowance

Tested on 4,025 real US broadband households’ metered traffic from the FCC’s Measuring Broadband America programme.

70%of last month’s heavy users stay heavy
90%of next month’s reached in the top tenth
30%were under the line the month before
0.98AUC for pace alone; the score matched it

Executive summary

Last month’s usage pace reaches 90% of next month’s heavy households in a tenth of the base, and a twelve-signal score adds nothing, so the offer list runs on the rule.

70%of heavy users stay heavy
90%reached in the top tenth
30%were under the line before

Situation

Plan upgrade offers land best the month before a household passes its allowance.

Approach

Last month’s pace against a usage score, tested on 4,025 real US households’ metered traffic.

Result

Pace alone reaches 90% in a tenth of the base; the score matched it.

The problem

An internet or mobile provider sells larger plans to households that are about to outgrow theirs. The usual trigger is a household that has already gone over its allowance, so the offer arrives after the bill shock. Providers that choose offers from recent usage, and send them before the limit, report better take-up than blanket campaigns, with the gains coming from offering the right size of plan rather than the biggest.

I measured how well last month’s metered traffic identifies the households that will exceed their allowance next month, so the offer can go out in time, against offering to everyone who was over last month.

Team
Head of base marketing, pricing, customer value management, CRM
Scale
Hundreds of thousands to millions of fixed broadband households
Systems
Usage records from the network, billing and plan catalogue, CRM and campaign tools
Measure
Share of next month’s heavy users offered in time; hit rate of the offer list

What I built

A monthly offer list from each household’s metered traffic: the month’s pace to a 30-day total, the last week against the first, the busiest days, the evening share and the Wi-Fi and upload shares. I compared a gradient-boosted score on those signals with the plain ranking by last month’s pace.

Usage recordsHourly householdtrafficMonth summaryPace, trend, busiestdays, sharesOffer listHouseholds rankedfor a plan offerCampaignOffer beforethe next bill
The list refreshes when the month’s usage closes.
Above a 1 TB pace last month70% reached, 70% hit rate70%Top tenth by last month’s pace90% reached, 44% hit rate90%Top tenth by usage score90% reached, 44% hit rate90%
The plain pace ranking reaches 90% of next month’s heavy users in a tenth of households. The usage score reaches the same share, so the list runs on the rule. Data: FCC Measuring Broadband America, raw data 2023

Results

I tested on the FCC’s Measuring Broadband America raw data usage records for January and February 2023: hourly traffic counted on each volunteer household’s test box, 4,025 households with at least 20 days of records in both months. The line was a pace of 1 TB a month; 4.8% of households were above it in February. The score was tested out of fold across five repeated splits.

Of the households above the line in January, 70% were above it again in February, and they made up 70% of February’s heavy users. The other 30% were under the line the month before, most of them close to it.

RankingAUC, all householdsAUC, households under the lineShare reached, top 5% of those under the line
Last month’s pace0.9750.94168%
Usage score, twelve signals0.9720.93266%

The usage score did not beat the plain pace ranking on any cut, with an AUC of 0.972 against 0.975. Heavy use is steady from month to month, so a pace line set a little under the allowance and widened to the top tenth is the offer list I would run. The score earns its place once offer responses are recorded and the question becomes who accepts, not who is heavy.

Data and method

Data
FCC Measuring Broadband America fixed raw data, January and February 2023, data usage records (curr_datausage): wired and Wi-Fi bytes sent and received by household devices, hourly. The FCC publishes the programme data for public use without restrictions.
Target
February traffic on a pace of 1 TB or more for a 30-day month
Population
Households with at least 20 days of records in both months; hourly counter readings above 450 GB removed as counter faults
Methods
Gradient-boosted classifier on twelve January usage signals; five-fold out-of-fold predictions repeated over five seeds
Comparisons
Households above the 1 TB pace in January; the ranking by January pace

Limitations

  • The panel is volunteer US households, and usage is counted on the test box, which can miss devices connected elsewhere.
  • Only two months of broad usage records are in the 2023 release, so the test is one month ahead and seasonal swings are not covered.
  • The target is heavy use, not acceptance of an offer. A live campaign records responses and refits on them.
  • Plan allowances differ by provider; the line is set to the provider’s own allowance in production.

How I would take it live

  • Pull three months of household usage and plan allowances from billing
  • Set the line under the allowance and size the list to the campaign
  • Run one cycle with a held-back group and record responses
  • Refit on accepted offers once a few cycles are recorded

Financial impact

Offers that reach heavy users in time

Base size and margin per upgrade are assumptions; the reach and hit rates are measured.

InputValueSource
Households200,000
Extra monthly margin per upgradeA$15
Heavy next month4.8%Measured
Reached by top tenth90%Measured

Calculation

  1. Heavy households a month9,689
  2. Reached by the list8,745

8,745 heavy households offered a plan each month before the bill

Acceptance is measured in the first campaign with a held-back group.

Implementation and rollout

One cycle from usage to a measured offer

  1. Weeks 1 to 2

    Pull

    Usage and allowances from billing.

    Pricing, Manaz

  2. Week 3

    Size

    Line set under the allowance; list sized.

    Base marketing, Manaz

  3. One cycle

    Run

    Offers sent with a held-back group.

    CRM

  4. After a few cycles

    Refit

    Score refitted on accepted offers.

    Head of base marketing

Tools

Network usage records, Billing and plan catalogue, CRM and campaign tools, Python, LightGBM

Team

  • Head of base marketing owns the offer
  • Pricing sets the plans
  • CRM runs the campaign
  • Manaz list and measurement

The timeline is a plan for a typical engagement; it depends on data access and how many systems are involved.

Risks and mitigations

What could go wrong in production, and the control for each

RiskMitigation
Panel dataProvider usage records in production.
Two monthsSeasonality checked over a quarter.
Heavy is not willingResponses recorded and refitted.
Allowances differLine set per plan.

Key takeaways

Key takeaways

  • Heavy use is steady month to month.
  • A pace line under the allowance is the list.
  • Widening to the top tenth reaches most heavy users.
  • A score earns its place on accepted offers.