Flexible integration
Two read-only paths—standard API and file upload—with no rebuild and no write-back to in-house systems. Most customers complete validation-stage analysis on file upload alone.
Four Capabilities · Four Agents
Four capability Agents forming the hub for risk analysis and verification
Strategy Sandbox, Model Diagnosis, Rejected Applicant Recall, and Feature Value Analysis—four independent Agents sharing one data foundation. Every conclusion carries its rationale, and every detail can be traced layer by layer, so risk judgment is always backed by evidence.
Capability Overview
Four capabilities, four kinds of problems, one foundation
Four seemingly independent tasks in fact share one data foundation and one set of analytical capabilities, forming an interconnected chain: sandbox validation points to the model, diagnostic findings feed back into value analysis, and recall gray releases flow back as new validation samples.
| Capability | When to use it | What goes in | What comes out |
|---|---|---|---|
| Strategy Sandbox | About to adjust a strategy, unsure of the impact | Historical decision data + rules / thresholds to adjust | Post-adjustment false-decline rate, miss rate, affected segments, rule risk alerts |
| Model Diagnosis | Model performance slipping, cause unknown | Model input inventory + decision outcomes + performance labels | Decay attribution, failed-feature inventory, alternatives, reproducible evidence package |
| Rejected Applicant Recall | Suspected false declines, afraid to lower the bar | Historical declines + high-quality segment performance | Similarity matching results, recall outcome analysis, recallable list, recall recommendation report |
| Feature Value Analysis | Data procurement renewal, value unclear | Invocation logs + model input inventory | Data source value metrics table (KS / IV / PSI / cost / lift), low-value source inventory |
The problem it solves
Before go-live, simulate on historical data to see how many false declines and misses a threshold or rule change would bring, then decide whether to ship; rule conflicts are scanned automatically, surfacing rules that fight each other or have had zero hits for months.
How it works
01
Scope the backtest Choose the strategy pool and time window; pull real decision data and performance labels.
02
Define the adjustment Edit thresholds, add or remove rules in the UI, and compare multiple plans.
03
Run the backtest Replay the decision flow over history to compute “what if the new strategy had been in place”—days compressed into hours.
04
Read results with evidence Compare misses, false declines, interception lift, and rule hits—every metric opens to show its basis.
05
Detect conflicts Scan rule relationships and flag contradictory, shadowed, and zero-hit rules.
What it tells you
If this rule’s threshold moves from 0.7 to 0.65, what happens to this strategy pool’s false-decline rate and miss rate, and which segment gets let in? Two rules in this pool are fighting each other—one declines while the other approves, and one of them over-declines high-quality customers, already flagged red in the corner. Three more rules have had zero hits in six months and can be retired.
Strategy Sandbox Agent Runs backtests, comparisons, and conflict detection around strategy adjustments, producing evidence-backed validation results.
The problem it solves
When model performance slips, it automatically builds a performance baseline and attributes the decay at feature level—pinpointing feature drift, segment shifts, or data-source degradation—then delivers a reproducible fix with expected gains. No more round after round of trial and error.
How it works
01
Build the baseline Compute current true performance, compare against the historical baseline, and quantify the decay.
02
Attribute at feature level Evaluate distribution drift, discriminative power, missing rate, and correlation feature by feature to find the ones dragging the model down.
03
Validate by cohort Break results down by segment to see whether the decay is global or concentrated.
04
Run ablation experiments Quantify the effect of removing a feature—confirming attribution by experiment, not conjecture.
05
Recommend the fix Alternative feature plan plus expected effect; the evidence package exports for on-premises reproduction.
What it tells you
This round of decay was driven mainly by drift in the “device score” feature, caused by iOS version changes over the past two months. Replacing it with “behavioral biometrics” recovers performance to a quantified level—a conclusion from a real, completed experiment that can be reviewed. Every conclusion ships with three layers of evidence: feature-ablation experiments, cohort validation, and raw records. The evidence package exports and reproduces 100% on the customer’s premises.
Model Diagnosis Agent Builds a reviewable attribution chain for model decay from baselines, feature experiments, and cohort validation.
The problem it solves
Historical similarity matching brings back high-quality customers who were falsely declined—real historical performance replaces prediction, producing verifiable, back-stoppable recall lists and risk references, so the team dares to approve and can still pull back.
How it works
01
Scope candidate declines From risk-control screening results, select “borderline declines”—applications rejected by rules but without strong risk signals.
02
Identify segments Segment the borderline declines, clarifying the dimensions on which they resemble high-quality customers.
03
Match against history Run multi-dimensional similarity matching against historically approved, well-performing customers. Every number comes from historical observation—observed values replace inference and estimation.
04
Analyze recall outcomes For each batch of candidates, produce the similarity distribution, recallable volume, and risk reference.
05
Issue the recall report Output the recallable list and risk reference report with matching rationale and applicable boundaries, for business staff to judge and confirm.
What it tells you
This declined application shares over 0.85 similarity with 1,247 high-quality customers, whose actual historical delinquency rate is 4.2%—an observed value, not a prediction. The system produces the recallable list and risk reference report, each with matching rationale and applicable boundaries. Every number presented comes from real observation in historical data—observation replaces inference, estimation, and black boxes, and the conclusions stand up to checking.
Rejected Applicant Recall Agent Finds verifiable similar references in real historical performance, forming traceable recall lists and risk references.
The problem it solves
Connect each data source’s invocation logs with the model input inventory, then compute KS / IV / PSI / cost / lift per source—flagging high-cost, low-lift sources, so every procurement investment has a measurable return.
How it works
01
Connect logs with the input inventory Establish which features each source contributes and whether they are actually used in the model.
02
Aggregate usage by source Count features provided, features actually used, and the utilization rate per source.
03
Compute value metrics per source KS / IV (discriminative power), PSI (stability), and lift (incremental model contribution)—all computed from real invocation logs and the input inventory.
04
Generate the value tracking table KS / IV / PSI / cost / lift for every source at a glance, refreshed monthly.
05
Recommend trade-offs Flag high-cost, low-lift sources and quantify the model loss if they are cut.
What it tells you
Which data sources truly deliver lift, which have contributed little for years while still being paid for, and which two overlap so heavily that one suffices. How much model accuracy is lost if a source is cut—a number computed from real invocation logs and the input inventory, backed by data. At the procurement table, the business team finally holds the evidence.
Feature Value Analysis Agent Puts invocations, model usage, performance, and cost into one value chain, continuously producing evidence for data procurement and governance.
Use Cases
Four capabilities covering the full business chain
The four capabilities embed across the full business chain, delivering continuously at every point of the front line—so the risk chain grows stronger with repeated refinement.
Strategy Sandbox Validate strategy impact before go-live
Credit application anti-fraud
When new fraud patterns emerge, see the full impact of an adjustment in the sandbox before deciding whether to ship it.
Credit approval rate optimization
Rehearse borderline approvals before go-live and see the trade-off between approval rate and risk.
Full model lifecycle
Validate with sandbox simulation before launch—no blind tuning.
Model Diagnosis Decay localization & repair evidence
Credit model governance
When a scorecard decays, locate the root cause and deliver reproducible repair evidence—no repeated trial and error.
Full model lifecycle
Monitor continuously after launch; decay is caught the moment it appears.
Rejected Applicant Recall Real matching for borderline segments
Credit application anti-fraud
Falsely declined customers are safely brought back through similarity matching and recall validation.
Credit approval rate optimization
Bring back borderline segments worth serving—from “rather over-decline” to “dare to approve, able to pull back.”
Feature Value Analysis Data contribution & procurement governance
Data source value assessment
Regularly compute each source’s true contribution and cost, grounding procurement negotiations in data—so every yuan spent on data procurement has a clear return.
See the capabilities in action Every business context differs. Upload desensitized data and run one product demo to see how the capabilities land in practice.
Start a Product Demo → Foundation & Deployment
Appliance deployment—data never leaves your environment
A single on-premises appliance is the unified carrier: it connects in-house data with the existing risk-control stack and, through the unified data foundation, analytical capabilities, and Agent runtime, powers four kinds of intelligent risk applications. The appliance runs alongside your existing risk-control system, focused on analysis and verification—making what you already have stronger.
Continuous evolution, independently controllable
Three classes of upgrades—Agent capabilities, foundation models, and platform features—iterate continuously, making the platform stronger with use. Upgrades change only “how analysis is done”; your strategies, models, variables, and historical data remain independently held and exportable at any time.
Security & compliance
Independently isolated data, clear permissions, and fully audited processes—aligned with the security standards of your existing risk-control system.
One appliance carrying data and capabilities, making the existing risk-control system stronger.
Get Started
One product demo to see the real chain of risk analysis
With desensitized scenario data, experience the full “analyze—verify—recommend” chain: locate the problem, present the evidence, and clarify the next tuning direction.
The demo uses desensitized data and never touches your production systems.