AI in Treasury
In treasury, a forecast that is usually right is still dangerous. What matters is knowing when the model is wrong — before the market, the ALCO or the supervisor finds out.
Format
Classroom · Virtual
Upcoming sessions
Pick a session to applyADMISSIONS OPENCity cohorts run once six delegates are nominated. Tell us your preferred month and we’ll confirm dates at least four weeks ahead — please hold travel bookings until then — or offer the nearest confirmed session, live virtual, or in-house. No payment until confirmation.
The programme
AI in Treasury is a two-day programme for treasurers, ALM and liquidity managers, dealers and treasury operations teams who want to judge where AI and machine learning can support bank treasury work — and where human judgement must stay in charge. It covers AI cash and liquidity forecasting, deposit behaviour and early-warning signals, machine learning in ALM and interest rate risk analysis, treasury analytics for dealing and operations, and the controls that surround them. Participants compare AI forecasts with established methods, challenge model outputs before acting on them, and weigh use cases on value, risk and readiness. The Basel Committee’s Principles for Sound Liquidity Risk Management and Supervision and its standards on interest rate risk in the banking book remain the reference points: AI can support those disciplines, but it does not move accountability away from treasury and the ALCO. Case studies and peer benchmarks run through both days. Delivered in English and French in Dubai, London and across the Middle East, Africa, Asia and Europe — and live online.
What you will do
Who attends
- Treasurers, deputy treasurers and heads of ALM in banks and financial institutions
- Liquidity managers, ALM analysts and members of ALCO secretariats
- Dealers and heads of money markets, FX and fixed income desks
- Treasury operations, middle office and treasury risk teams
- Treasury analytics and finance professionals who support ALCO reporting, and internal auditors who review treasury
- Participants should know the basics of bank liquidity and interest rate risk; no programming or data science background is required
Programme agenda
Structured around one question — would you act on this forecast? — day one where AI supports treasury, day two challenge, risk and choosing use cases
I.Where AI fits in bank treasury
- The treasury decision chain, from cash positioning to ALCO, and where AI can enter it
- Prediction, automation and generative AI: three different tools with three different risks
- What the Basel Committee’s liquidity principles and IRRBB standards still require of people, whatever the tool
II.AI cash and liquidity forecasting
- Intraday and short-term cash flow forecasting: what machine learning adds to time-series and rule-based methods
- Forecasting through stress and regime change, when history stops being a guide
- Measuring forecast quality: error, bias and the cost of a miss in buffers and funding
III.Deposit behaviour and early-warning signals
- Machine learning estimates of non-maturity deposit behaviour, and how they compare with established approaches
- Liquidity early-warning indicators and anomaly signals: what to watch and where thresholds sit
- False alarms and missed signals: weighing the two errors
IV.Machine learning in ALM and interest rate risk
- Prepayment and behavioural assumptions: where machine learning sharpens them and where it hides them
- Scenario generation for liquidity and interest rate risk, and its limits
- Telling the ALCO what the model does and does not know
V.Treasury analytics for dealing and operations
- Pricing, client-flow and market analytics on the dealing desk
- Payments, reconciliation and settlement exceptions in treasury operations
- Generative AI for market commentary and treasury reporting, and the checks it needs
VI.Challenging outputs and managing model risk
- Back-testing, validation and drift monitoring for treasury models
- Explainability for the ALCO: an output nobody can explain is not a basis for a funding decision
- Vendor tools and third-party concentration, a vulnerability the FSB’s November 2024 report on AI singles out
VII.Comparing use cases on value and risk
- Value, risk, data readiness and the cost of control: one scale for every proposal
- The business case that survives the ALCO and the chief risk officer
- Sequencing: which use cases first, and which to leave for later
VIII.Integrated case study
- A bank treasury is offered three AI proposals: a liquidity forecast, a deposit-behaviour estimate and a dealing analytics tool
- Challenging each one on evidence, explainability, data and vendor risk
- Arguing a priority order before a mock ALCO
Frequently asked
What is AI in treasury?
It is the use of artificial intelligence and machine learning to support treasury work — cash and liquidity forecasting, estimates of deposit behaviour, early-warning signals, market and client-flow analytics, and the automation of treasury operations. In a bank, it sits inside disciplines the Basel Committee has set out for liquidity and interest rate risk, so every AI output still needs an owner, a challenge and an audit trail.
What changes for treasury when AI is introduced?
The regulatory expectations do not change: the Basel Committee’s Principles for Sound Liquidity Risk Management and Supervision and its standards on interest rate risk in the banking book still apply, and accountability stays with treasury and the ALCO. What changes is the risk profile of the tools. The Financial Stability Board’s November 2024 report on the financial stability implications of AI highlights third-party dependencies and service provider concentration, and model risk, data quality and governance — questions a treasury now has to answer about its own tools.
Is this an ALM course?
No. It assumes participants already know the basics of liquidity and interest rate risk management, and it focuses on where AI supports that work and how to challenge it. For the ALM discipline itself, BIZENIUS runs separate ALM, liquidity and treasury programmes.
What level is the programme, and do I need to code?
It is for treasury and ALM practitioners and their managers. No programming or data science background is needed: the focus is on judgement — what to ask of a forecast, its data and its vendor before acting on it.
Can it run live virtual or in-house?
Yes. Public cohorts run in the classroom and live virtual. For one institution, the programme can run in-house as a custom programme, scoped on request, in English or French.
Is there a group rate, and do delegates receive a certificate?
Institutions sending several delegates, in one cohort or across the year, receive group terms; fees are provided on enquiry. Each participant receives a BIZENIUS Banking Academy certificate of completion. The programme is practice-led rather than exam-led and is not preparation for a third-party qualification.
Who teaches this
Practitioners, not presenters.
Led by practitioners who hold, or have held, the seats this programme prepares you for: group treasurers and heads of asset–liability management, chief risk officers, heads of credit and capital management, and former central-bank supervisors who examined the very frameworks they now teach. Between cohorts the same people advise banks on those frameworks, so what you learn is what is being defended in front of boards and regulators today.
What the bench brings
- ALCO practice and treasury policy
- Funds transfer pricing design and restructuring
- IRRBB measurement: EVE and NII sensitivity
- Liquidity risk: LCR, NSFR and contingency funding
- AI and machine learning applied to financial services
- Data science and big-data practice
Where they have practised
Current and former practitioners — people who hold the seat today alongside those who have held it.
Sectors: Banking & financial services · Technology & fintech · Professional services · Central banking & supervision
Regions: Africa · the Middle East · Europe · Asia · the Americas
How they teach
- Live case studies from real institutions
- Worked exercises on realistic bank data
- Regulator-style challenge sessions
- Group problem-solving on realistic institutional cases
- Knowledge checks and a personal action plan
Cohorts are kept small so every exercise is worked on the participants’ own situations — in person or live virtual.
The faculty profile for your cohort is sent with the full agenda and the next dates when you enquire.Request brochure →
Share this programme
Know the right person for this seat?Nominate a colleague →
Planning 2027 for your team?Request the 2027 training calendar →
In their words
Knowledge transfer, emphasised throughout
“We worked with BIZENIUS for our Fresh Graduates Programme — they are simply amazing. Knowledge transfer and practical learning were emphasised throughout.”
Kuwait Investment Authority
From the Mandate Record
Mandate № 01 · Africa
The training programme that became national regulation
What the team mastered, the regulator wrote into the rulebook.
Open the dossier →
The Capability Arc™
Fix it · Advisory
Balance-Sheet Management — ALCO, ALM & FTP
When the institution wants the work done with it — an ALCO that decides, ALM that manages both sides of the balance sheet, and the forecasts and assumptions behind them.
Automate it · Smart IT
AI Build & Deployment
When a forecasting or early-warning tool has to go live inside the treasury’s controls — monitored, explainable and auditable.
Learning is one point on the Capability Arc. Many institutions pair this programme with the advisory engagement — and automate what the framework demands.
Teams from these institutions train with BIZENIUS
Related programmes
Asset and Liability Management (ALM) Masterclass
ALM after Silicon Valley Bank — liquidity risk, IRRBB under Basel 4, FTP and cost-of-funds discipline for banks whose safest assets can still sink them.
View programmeAdvanced Treasury, ALCO Strategy, Liquidity Stress Testing & Profitability Protection Masterclass
A bank can look liquid and still leak margin quietly — two days that connect Treasury, ALCO, liquidity stress testing, FTP, IRRBB, deposit behaviour and funding cost into one balance-sheet decision framework that protects profitability.
View programmeMachine Learning in Banking and Finance Masterclass
What machine learning can and cannot do for banking and risk — supervised and unsupervised methods, alternative data and explainable AI, worked in practice.
View programmeBackground reading on this subject
Written by the practitioners who lead the programme — read before you enquire.
Choosing AI use cases that survive a business case
Most AI pilots fail for reasons visible before they start. The four tests a candidate use case has to pass, why the pilot-to-production gap is an engineering and governance gap rather than a modelling one, and how to rank a roadmap honestly.
Read more →GuideHow to validate an AI model you cannot look inside
When the mechanism is unreadable or the vendor will not show it, validation shifts from inspecting the model to interrogating its behaviour. The tests that work, what to demand at procurement, and when the honest answer is a restriction rather than an approval.
Read more →InsightLiquidity early warning indicators: what to measure and where to set thresholds
The indicator families that deteriorate before a regulatory ratio does, how to calibrate thresholds so they fire while management still has options, and why an indicator without a named owner is decoration.
Read more →Banking & Finance
Take the brochure with you.
One request — the full agenda, the faculty and the next cohort dates, sent personally by the admissions team.