Skip to main content
Back to challenges
Challenge

Build a High-Frequency Trade Settlement Anomaly Detector with Vercel AI SDK

New regional stock exchanges require real-time settlement monitoring to prevent systemic failure and trade wash manipulation. Build a TypeScript trade settlement anomaly agent using Vercel AI SDK to stream, parse, and flag anomalous trade fills with under 30ms latency.

CybersecurityHosted by Vera
Sign in free to start
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

Deploy a TypeScript Vercel AI SDK agent on edge execution environments to perform real-time wash trade detection on stock exchange settlement streams.

Delivery guide

How work is evaluated

Evaluation

Evaluates wash trade pattern detection recall and streaming latency metrics.

Datasets

Challenge datasets

Public datasets, plus the private datasets you have access to.

Evaluation rubric

How submissions are scored

These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.

Dimensions
2 scoring checks
Binary
2 pass or fail dimensions
Ordinal
0 scaled dimensions
Dimension 1

wash_trade_recall_test

Must flag self-dealing orders (same buyer and seller ID).

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Dimension 2

execution_latency_ms

Stream latency per trade fill block. • target: 18 • range: 0-30

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Learning goals

What you should walk away with

  • Implement ultra-low latency streaming functions using Vercel AI SDK

  • Build wash trade pattern detection algorithms over stock exchange order books

  • Deploy edge-based settlement anomaly detectors using TypeScript and Zod

  • Achieve sub-30ms execution processing latency per trade execution block

Resources and assets

Reference links and supporting material

Dataset notes

Dataset of stock exchange trade order streams with injected wash trades, layer spoofing, and settlement delays.

Challenge setup

Evaluates wash trade pattern detection recall and streaming latency metrics.

Challenge input

JSON order book trade fill event array

AI SDK

Enables ultra-fast TypeScript stream processing on edge nodes.

Evaluated output

JSON manipulation detection verdict, flag type, and latency in ms

Evaluation checks
  • Must flag self-dealing orders (same buyer and seller ID).
  • Stream latency per trade fill block. • target: 18 • range: 0-30
Configured evaluation evidence
  • Benchmark: Market Surveillance Suite 2026
  • Execution Latency Ms target: 18
  • 1 public reference case
Configured runtime
  • JavaScript execution harness
  • javascript sandbox (unavailable on Versalist)

Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.

View technical recipe

Configured tools

Action Space
  • Vercel AI SDK · Required
Orchestration
  • Vercel AI SDK · Required

Evaluation contract

  • wash_trade_recall_test · Weight 1
  • execution_latency_ms · Weight 1

Metrics

  • execution_latency_ms · Target 18

Benchmarks

  • Market Surveillance Suite 2026
  • security

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON order book trade fill event array

    Output: JSON manipulation detection verdict, flag type, and latency in ms

    Execution harness: JavaScript

Evaluation tools

  • AI SDK · Streaming Engine

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Build a High-Frequency Trade Settlement Anomaly Detector with Vercel AI SDK