- BFSIBanking, Financial Services & Insurance
- HealthcareComing soon
- ManufacturingComing soon
- Retail & E-CommerceComing soon
Lending
The statement was a PDF. Anyone could have edited it — Signzy Lending pulls bank data through India's Account Aggregator framework — structured, verifiable, and carrying a consent record instead of arriving as an emailed PDF.
Buy through TechBag
Same software. Better outcome — at a lower cost.
How it’s rated
Full scoreboard ↓Quick answer
The Signzy API family
This page covers Lending — Account Aggregator and analysis. The rest of the marketplace:
Quick facts
30-second orientation- Product
- Lending — Account Aggregator and analysis
- Inside it
- AA APIs, risk assessment, bank statement analysis
- The shift
- Consent-based data, not emailed PDFs
- Why it matters
- Provenance is part of a defensible decision
- Honest scope
- It supplies inputs; your credit policy decides
- Model risk
- Explainability and fair lending stay yours
- Pricing
- Quote-only — typically per data pull
- In India via
- TechBag — INR/GST, scoping and support
Understand alternative underwriting before you buy it
Most product pages skip this. We start here — so you buy a capability, not a buzzword.
What is Signzy Lending?
Consent-based bank data and the signals derived from it — income regularity, obligations and cash-flow shape, with a consent artefact recording what was shared and why.
An emailed PDF vs a consented pull — the honest table
What consolidation actually replaces, dimension by dimension.
| Dimension | PDFs emailed by the borrower | Lending (Signzy) |
|---|---|---|
| Income proof | PDFs emailed by the borrower | AA data, direct from the bank |
| Provenance | Unknown and uneditable | A consent artefact with the pull |
| Parsing | Whatever format arrives | Structured on retrieval |
| Fraud context | A separate system | Onboarding signals on the same contract |
| Audit answer | Reconstructed under pressure | Recorded when it happened |
| What it is NOT | — | Not your credit policy, and not your model risk |
Account Aggregator is a PUBLIC framework: everyone retrieves the same data, so the analysis is what you are buying. Backtest it. And model risk, explainability and fair-lending scrutiny remain entirely yours.
The five pieces of the platform
Vendors love diagrams; buyers need to know what they’re actually operating. Here’s the whole platform, demystified.
Account Aggregator
India's consent framework lets a borrower authorise their bank to share statement data directly with a lender. Structured, verifiable and accompanied by a consent artefact rather than a PDF of uncertain origin.
Bank statement analysis
Deriving income regularity, obligations, bounce history and cash-flow patterns from raw transactions. The analysis quality matters more than the data access, since everyone can access the same data.
Risk assessment
Combining the derived signals into something a credit team can act on. It informs a decision your policy makes — the thresholds, exclusions and approvals stay entirely on your side.
The consent artefact
The record of what the borrower authorised, for what purpose and for how long. Easy to treat as plumbing, and it is part of the answer when a regulator asks how a decision was reached.
One telemetry fabric across endpoint, cloud, and network — threats correlated once, not chased console to console.
Six capabilities. Consent, derive, assess.
Signzy Lending reads cash flow with consent — income, obligations and the portfolio, and paired with the human firewall.
Consent-based bank data
Pulling statement data through India's Account Aggregator framework, so it arrives structured and with provenance rather than as an email attachment the borrower assembled.
Income, obligations, bounces
Deriving regularity of income, existing obligations, bounce history and cash-flow shape from raw transactions. This interpretation is where vendors actually differ.
A view, not a verdict
Signals combined into a credit view your team can act on. The thresholds, exclusions and approval decisions remain entirely within your own credit policy.
The artefact that survives audit
What the borrower authorised, for what purpose, for how long. Part of the answer when a regulator or ombudsman asks how a lending decision was reached.
Identity already verified
Because lending sits on the same marketplace as onboarding, the borrower's identity checks and any fraud signals are available to the credit decision rather than in another system.
What you can show later
Which data was pulled, under what consent, and what the assessment returned. In lending, being able to reconstruct a decision matters as much as making it well.
Everyone gets the same data. Not the same reading.
Here’s what genuinely sets it apart — and exactly where it stops.
Account Aggregator changed the input, and the audit
Before India's Account Aggregator framework, obtaining a borrower's bank statements meant asking them to email PDFs — documents of uncertain origin, trivially editable, arriving in whatever format their bank produced and requiring parsing work before they were usable. AA lets the borrower consent to their bank sharing the data directly, so it arrives structured, verifiable and with a consent artefact attached. Two things improve simultaneously. The credit model gets cleaner inputs, which is the obvious gain. Less obviously, the lender gets a record of exactly what was shared, by whom, for what purpose and for how long — and when a regulator or an ombudsman asks how a decision was reached, the provenance of the input data is part of a defensible answer. Ask any vendor how they use AA data rather than whether they support it.
Everyone can read the same statements — the analysis is the product
Account Aggregator is a public framework, so data access is not a differentiator: any licensed participant can retrieve the same statements. What separates vendors is what they derive from them. Identifying that an income credit is salary rather than a transfer between the borrower's own accounts, recognising a seasonal business pattern rather than declining volatility, spotting existing obligations that do not appear on a bureau file, distinguishing a genuine bounce from a bank error — these interpretive judgements determine whether the output improves a credit decision or merely restates the statement. When evaluating, ask to see the derived signals on a sample of your own historical borrowers with known outcomes, because that comparison reveals analysis quality in a way a feature list cannot.
The identity work is already done
Because lending sits on the same marketplace as the onboarding and fraud APIs, a borrower who was verified at onboarding does not need re-verifying at the credit step, and any fraud signal raised during onboarding is available to the credit decision. That sounds administrative and has a real effect: in many lenders, identity, fraud and credit run as separate systems with separate integrations, and a fraud flag raised in one is invisible to the others until someone notices manually. Consolidating them onto one contract removes an integration and a category of missed signal. The honest caveat is that this advantage only materialises if you actually buy the other lines — as a standalone lending purchase, Signzy competes on analysis quality alone.
The decision, the model risk and the fairness obligation stay yours
This is the boundary that matters most in lending. The platform supplies data access, derived signals and an assessment; your credit policy defines thresholds, exclusions and what is actually approved. Everything downstream remains your responsibility, and that responsibility is heavier here than in most software categories. You own model risk governance. You own explainability when a borrower or an ombudsman asks why they were declined. You own fair-lending scrutiny, which matters particularly with alternative data — signals derived from transaction behaviour can correlate with characteristics you are not permitted to lend on, without anyone intending it. Ask what explainability and monitoring documentation you receive for your model risk committee, and budget to produce the remainder yourself rather than discovering the gap at your first model review.
The numbers behind the platform
What your lending rollout looks like
Decide what you cannot see today
Income you cannot verify, obligations off the bureau file, or borrowers with no history at all. Each points at a different part of this line.
Get the AA consent flow right
It is part of the borrower journey and part of the audit trail. A clumsy consent step costs completions; a sloppy record costs you the audit answer.
Backtest on your own book
Run the derived signals against loans whose outcomes you already know. Everyone reads the same statements, so this is the only real test of the analysis.
Write the policy around the signals
Thresholds, exclusions and what a score actually triggers. The model informs; your policy decides, and that document is what a regulator will read.
Assemble the model risk file
Explainability, monitoring, drift and fair-lending review. Ask what you receive and budget to produce the rest before your first model review, not after.
Review outcomes by segment
Alternative signals can correlate with characteristics you are not permitted to lend on. Test for that on a schedule rather than when somebody complains.
The review scoreboard
Modelled on Gartner Peer Insights structure. *Counts and breakdowns are illustrative pending verified review collection.
Quick poll — what’s driving your evaluation?
Talk to an advisor“The consent trail mattered more than we expected. When our auditors asked how we sourced income data, it was a record rather than a reconstruction.”
“Backtest against your own book before you commit. The derived signals looked good in the demo and we needed to see them against loans whose outcomes we knew.”
“Ask what documentation you get for the model risk committee. We had to produce a fair share of the explainability material ourselves.”
“AA access is a level playing field — every vendor gets the same statements. What we were actually buying was the interpretation, and that is worth testing properly.”
Where everyone sits — the grids
Analyst firms bury this view behind paywalls, and G2 retired its Grid. So here’s TechBag’s synthesis of the alternative lending data market — tap any vendor to see why it sits where it does.
TechBag Alternative Lending Grid
Execution strength vs product vision — the classic market map, minus the paywall.
AA with consent trail, on one contract.
Detection × Portfolio Integration
The grid nobody publishes — quality of the derived cash-flow signal vs the strength of the consent and audit record.
Derived signals plus the audit artefact.
Positions are TechBag’s illustrative synthesis of public review-platform data and vendor documentation — not a reproduction of any analyst graphic. Verify before relying on it.
Lending vs the alternatives
Against emailed statements, a bureau score alone and an in-house AA build — on provenance, analysis and who owns the decision.
| Dimension | Signzy Lending | Emailed statements | Bureau score alone | In-house AA build |
|---|---|---|---|---|
| Data provenance | AA with consent record | Unknown | Bureau-sourced | AA, yours |
| Income visibility | Derived from cash flow | Manual reading | None | Yours to build |
| Analysis quality | Test it yourself | Analyst judgement | N/A | Your data science |
| Who owns the decision | You do | You do | You do | You do |
| Model risk documentation | Ask for it | Human rationale | Bureau-supplied | Yours to produce |
| India data residency | Named region | Your inbox | In India | Your servers |
Which cybersecurity approach fits you?
Honest fit signals — because the fastest way to lose your trust is to pretend one product wins every scenario.
Choose Signzy Lending if…
- ✓You want consent-based bank data with an audit trail, not emailed PDFs
- ✓Onboarding or fraud already runs here, so identity and fraud signals reach credit
- ✓You will backtest the derived signals against your own book before committing
- ✓India data residency matters for financial data — Signzy names it, many do not
A bureau score may be enough if…
- ✓Your book is entirely borrowers with established formal credit history
- ✓You have no appetite for the model risk governance alternative data requires
- ✓Volumes are low enough that manual statement review remains workable
Do not expect…
- ✓AA access to be a differentiator — it is a public framework; the analysis is the product
- ✓Model risk, explainability or fair-lending scrutiny to transfer to the vendor
- ✓The same-contract advantage unless you actually buy the onboarding or fraud lines
What does unverifiable income cost you?
Drag the sliders (monthly applications; average loan margin). Estimates model applicants declined for unverifiable income plus the manual effort of reading statements by hand. Illustrative.
Loaded cost = salary + overheads per productive hour. Illustrative only — your TechBag quote models your actual environment and modules.
Three ways to consume it
Quote-only — Signzy publishes no price. TechBag scopes the billing unit, the AA integration and the backtesting effort, then quotes in INR with GST.
Lending
Best when you cannot verify income
- Account Aggregator with a consent trail
- Income, obligations and bounce signals
- Records that survive an audit
+ Platform add-ons
Best for a broader rollout
- Scoped to your estate
- Add-on modules as needed
- Phased, right-sized deployment
+ the wider marketplace
Best across the journey
- Borrower already identity-verified
- Fraud flags reach the credit decision
- One contract, not three integrations
Buy it for less — TechBag pricing beats list
Whatever the list prices above, TechBag negotiates a significantly better deal — with GST-compliant INR invoicing and local support. Ask us for your discounted quote.
Get an India-ready quote
Tell us your requirements and current tools — we’ll model it against what you spend today.
The 8 questions to ask every vendor
Take this into your next vendor call — including ours.
What can you not see today — income, hidden obligations, or no history at all? Each points at a different capability.
Can you run the derived signals against loans with known outcomes? AA access is universal; the interpretation is what you are buying.
Is the AA consent step clean for the borrower, and does it produce the record you will need at audit?
What explainability and monitoring material do you receive for your model risk committee? Expect to produce some yourself.
How will you test that derived signals do not correlate with characteristics you cannot lend on? That obligation is yours.
Is it documented that the model informs and your credit policy decides? A regulator will ask to see that.
Is in-country storage documented for your deployment? Bank statement data is sensitive under DPDP.
Is billing per consent, per pull or per assessment? Nothing is published, and the unit changes the economics at volume.
Questions buyers ask
Ready to evaluate Signzy Lending?
Backtest the derived signals against loans whose outcomes you already know — every vendor reads the same statements — or let a TechBag advisor scope the AA integration and the model risk file.
Stats, ratings, review counts and pricing are illustrative and sourced from public materials; verify before purchase.