Credit risk & churn analytics
Here's what AI can do for this role — and what still needs a human. Built straight from ENSEK's own job advert, running live on my_db.ensek_demo.accounts — 27,640,145 real rows via MotherDuck (DuckDB). Not a slide about AI. The job, getting done.
Every line on the left is lifted from ENSEK's actual job ad. If a card lacks a harvested JD line, it is omitted. On the right is the AI doing it — with eligible cards running live against the warehouse and offline inspection clearly labelled in the workspace.
“Own and evolve the credit risk product strategy, vision and roadmap across the full customer lifecycle”
What is the churn risk distribution across the 27.6M account book — accounts, revenue at stake and arrears overlap per tier?
bar chart“Define and prioritise initiatives spanning acquisition, in-life risk management and collections strategies”
How does the arrears book concentrate by churn tier — which tier carries the highest per-account debt and total exposure?
table“Translate complex regulatory requirements (FCA, Ofgem, ICO) into clear, actionable product deliverables”
What is the tenure profile by churn tier — are short-tenure accounts concentrated in the Critical cohort?
bar chart“Partner with engineering to scope, size and deliver scalable, data-driven capabilities”
How does churn and arrears risk vary by area affluence — is lower-value postcode a credit risk predictor?
bar chart“Use data to define KPIs, dashboards and performance frameworks, driving continuous improvement”
What is the credit posture of the full book — arrears rate, mean revenue, debt book and tenure by churn cohort?
kpi“Collaborate with clients and stakeholders to ensure the product addresses real-world credit and collections challenges”
Show the in-arrears accounts ordered by balance — the working collections list with churn risk grade.
deviationThe honest other half. AI does the analysis; a person owns the decision — especially where regulation, fairness and accountability bite.
A plain-English question — the same one the job ad describes — is translated to SQL by the agentic backend.
Curated cards run server-side against MotherDuck when eligible. The workspace separately labels any local inspection path.
Runs against my_db.ensek_demo.accounts (27,640,145 rows declared by the manifest). No synthetic numbers.
Each figure carries a falsifier — recomputed from the result set, not a stored number, so it can't quietly drift.
It's the role getting done: curated questions run live server-side against the warehouse; local inspection is labelled inside the workspace.
Open the live workspace →Provenance. Local fallback: 5,000-row verification dataset seeded to real distributions (3.5% Critical churn, 8.3% arrears, affluence×churn correlation). Live path queries the full my_db.ensek_demo.accounts (27,640,145 rows) server-side via MotherDuck. No PII: account_ref, address, postcode excluded. account_balance_gbp positive = owes money (in-arrears), negative = in credit.
It's Sorted — I took ENSEK's job ads and didn't write a report on what AI could do. I built it. Get the rest sorted →
I'm trained on this proof and the real ENSEK: the Ignition meter-to-cash platform (seven modules), the move under Centrica in 2024, 7M+ energy accounts migrated for suppliers like British Gas and Utility Warehouse, and the Ofgem framing. Ask me how the Data Analyst function changes shape, or which open roles map to which Ignition module.