Fligoo AI Services

Solution · Collections for banking & fintech

Collections that start before the first missed payment.

Most collection strategies still run on rules and deciles: everyone in the same bucket gets the same call, on the same day, with the same message. We replace that with a decision system — predictive models that know who will pay, who will pay because you acted, and how to reach them — and agents that execute the treatment across WhatsApp, voice, SMS and email, inside your policy and your regulator's rules.

  • 01 · SharpAI

    Predictive models

    9 models · foundational + downstream

  • 02 · AUTONOMY

    Agents

    9 agent patterns in this vertical

  • 03 · FDE

    Engineering services

    2 anonymized engagements

The delinquency lifecycle

Collections is where the problem becomes visible. Delinquency is where it starts.

Every stage of the lifecycle has its own decision, its own cost of contact and its own window. One model per stage, one shared view of the customer behind all of them.

  1. 01

    Current · pre-delinquency

    Early warning

    Detect payment stress weeks before the due date, from the customer's own behavior — not from a bureau trigger that arrives late.

    Decisions we model

    • Payment-stress score
    • Preventive offer or reminder
    • Limit and exposure review
  2. 02

    1–30 days past due

    Early collections

    Separate the customers who will pay on their own from the ones who need a nudge — and leave the first group alone.

    Decisions we model

    • Self-cure probability
    • Soft reminder timing
    • False-delinquency detection
  3. 03

    31–90 days past due

    Mid-stage collections

    Concentrate effort where the action changes the outcome: the right channel, the right moment and the right message per customer.

    Decisions we model

    • Treatment uplift
    • Best channel and moment
    • Promise-to-pay follow-up
  4. 04

    90+ days past due

    Recovery & renegotiation

    Offer the plan the customer can actually keep, and decide what to work in-house and what to place with an agency.

    Decisions we model

    • Renegotiation propensity
    • Payment capacity
    • Optimal discount or plan
  5. 05

    Every stage

    Learning loop

    Every contact, promise and payment feeds back into the models. The last conversation is not noise — it is context for the next action.

    Decisions we model

    • Challenger vs. champion
    • Message optimization
    • Contact saturation guardrails

01 · SharpAI · Collections

One customer foundation, a decision head for every collections question.

Collections heads attach to the same Customer Behavior Transformer we use across banking. The embedding already encodes how each customer earns, spends, pays and responds — so the collections models start from a rich view of the customer instead of a handful of bureau variables, and each head answers one operational question.

Foundation · what the backbone tokenizes

Every signal the backbone reads about the debtor.

The customer's event history across accounts, cards, loans, channels and past collection interactions. Hover or tap any signal to see what it is.

27 signals

Downstream · what the head consumes

What the treatment-uplift head consumes.

The uplift head does not ask who is likely to pay. It asks who pays because of the action. Hover any node — these are the inputs behind one treatment decision.

13 signals

Foundation models · self-supervised pre-training, frozen backbone reused downstream

  • Customer Behavior Transformer (CBT)

    The shared banking backbone. It tokenizes each customer's event history — transactions, income, balances, payments, channel touches and prior collection interactions — into a sequence the encoder reads, and produces the customer embedding every collections head consumes.

    Transformer encoder over the latest customer events · 256-dim shared embedding · positional + temporal encoding

    Pre-training objectives

    • Masked event modeling
    • Next-event prediction
    • Temporal contrastive

    Corpus · Fine-tuned on each institution's own portfolio inside its own cloud · pseudonymized data · works from the data available on day one and improves as the loop feeds back

    Tokenized inputs
    Account, card and loan events · Income and payment behavior · Channel and collection interactions
    Outputs
    Per-customer behavioral embedding · Sequence representation for collections heads

Downstream heads · fine-tuned on the frozen foundation embedding per institution and use case

  • Delinquency risk

    Probability of entering delinquency at 30, 90 and 180 days — the early-warning signal that opens the lifecycle.

    Survival head over the frozen embedding

    • Early warning
    • Risk
  • Probability of payment

    Who pays, and when, without any action — the baseline every treatment is measured against.

    Calibrated classification head

    • Self-cure
    • Prioritization
  • Payment capacity & stress

    Estimates how much the customer can realistically pay now, from income and spending patterns.

    Regression head on cashflow features

    • Capacity
    • Affordability
  • Treatment uplift

    The incremental effect of each action on each customer — so effort goes to the people it changes, not the ones who would pay anyway.

    Uplift modeling · T-learner and X-learner

    • Uplift
    • Cost-to-collect
  • Best contact moment

    The channel and time window in which each customer is most likely to respond.

    Ranking head over channel response history

    • Channel
    • Timing
  • Message optimization

    Chooses tone, content and offer framing per customer and keeps learning from every response.

    Contextual bandit

    • Messaging
    • Experimentation
  • Renegotiation propensity

    Which customers will accept a payment plan or refinancing, and which plan structure they are most likely to keep.

    Propensity head + plan-structure ranking

    • Renegotiation
    • Recovery
  • Promise-to-pay

    Probability that a promise will be kept, so follow-up is scheduled where it matters.

    Classification head over conversation and payment history

    • Promise-to-pay
    • Follow-up

02 · AUTONOMY · Collections

Foundation models predict. AUTONOMY decides, executes and learns.

Prediction creates insight; decision and execution create impact. A team of specialized agents, coordinated by supervisory agents, turns each score into a treatment — and every treatment runs through the institution's policy, consent and compliance rules before it reaches the customer.

9 agent patterns · ordered by deployment maturity

  1. A01

    Early Warning Agent

    Monitors payment-stress signals on current accounts and opens a preventive play before the due date — a reminder, a rescheduled debit date or an offer.

    Trigger · Stress score threshold

    ↳ Delinquency prevented, not chased

  2. A02

    Soft Reminder Agent

    Sends the lightest effective nudge to early-stage customers likely to self-cure, and stays silent where silence works better.

    Trigger · Due date / 1–30 days

    ↳ Lower contact cost

  3. A03

    Prioritization Agent

    Ranks the daily portfolio by incremental recovery per contact and assigns each account to agents, dialer, digital or no action.

    Trigger · Daily portfolio refresh

    ↳ Effort where it moves recovery

  4. A04

    WhatsApp Collections Agent

    Holds the conversation on WhatsApp Business — approved templates, opt-in and 24-hour window enforced — explains the balance, shares payment links and answers questions.

    Trigger · Treatment assigned to WhatsApp

    ↳ Self-service resolution

  5. A05

    Negotiation Agent

    Proposes the payment plan the customer can keep, within the discount and term limits the institution has authorized.

    Trigger · Renegotiation propensity

    ↳ Plans that are kept

  6. A06

    Promise-to-Pay Agent

    Registers each promise, schedules the follow-up and adapts the next step if the payment does not arrive.

    Trigger · Promise registered

    ↳ Higher kept rate

  7. A07

    Escalation Agent

    Hands the case to a human collector — with full context and a recommended next step — when the conversation, amount or vulnerability signal requires it.

    Trigger · Policy or judgment threshold

    ↳ Humans on the cases that need them

  8. A08

    Compliance Agent

    Checks every action before it executes: contact hours, frequency caps, consent, do-not-contact lists, message wording and data-protection rules.

    Trigger · Every action

    ↳ Auditable by design

  9. A09

    Learning Agent

    Reads the outcome of every contact and feeds it back into the models and the strategy, running champion-versus-challenger tests continuously.

    Trigger · Continuous

    ↳ A strategy that improves every cycle

03 · FDE · Collections

A collections challenger, run by engineers embedded in your team.

We do not ask you to switch off what works. We run a controlled challenger against your current strategy — on your portfolio, in your cloud, through your channels — and measure incremental recovery against a control group. This is not body-shopping. It is forward-deployed engineering.

Integration with your collections stack

Core banking, card processor, rule engine, CRM, dialer and collection agencies — connected read-only first. Model outputs land in the systems your team already operates, replacing fixed deciles with as many treatments as the data supports.

Challenger design

A control group on your current strategy and test arms that separate the effect of better models from the effect of better execution — so every point of recovery is attributable.

Omnichannel execution

WhatsApp Business, voice, SMS, RCS, email and call center orchestrated from one decision layer, with frequency caps and contact windows enforced at the orchestration level.

Compliance and data protection

Pseudonymized data, consent and opt-out management, contact-hour rules and a full audit trail of every decision — aligned to local consumer-protection and data-protection regulation (LGPD in Brazil, Ley 25.326 in Argentina).

KPIs that finance trusts

Recovery rate, incremental recovery, promise-to-pay kept rate, recovery per contact and cost-to-collect — with guardrails on complaints, opt-outs and contact saturation.

90-day path to production

Two weeks of scoping, then modeling, controlled execution and a results-backed business case. We can start with limited data and grow the scope as the loop proves itself.

Anonymized engagements · same engineering team end-to-end

  • Retail bank · LATAM

    Loan and card portfolios

    Model-driven segmentation of the collections portfolio to replace rule-based deciles with finer treatments loaded into the bank's rule engine and CRM — including detection of administrative false delinquency and multi-loan customers. Runs inside the bank's cloud.

    In delivery — impact measured pre/post against the current rules.

  • Top 5 telco · LATAM

    B2B invoice portfolio

    Payment and non-payment prediction per invoice, with probability-based prioritization and best-channel strategy, validated offline on the operator's historical data.

    10.7% potential collection lift identified in offline validation.

Team shape — typical FDE composition for this vertical

  • FDE LeadSenior · embedded
  • Senior Data Scientists2 · risk + uplift
  • Data Engineer1 · core + channels
  • Agent Engineer1 · AUTONOMY + WhatsApp
  • Collections Strategy Lead0.5 · treatments + KPIs
  • Compliance Liaison0.5 · policy + audit

Bring SharpAI, AUTONOMY and FDE to your operation.

Embedded senior engineers, predictive models in production, and agents that execute on every score.

Talk to our team
Collections for banking & fintech — Fligoo AI Services