Global Equities Pattern-Recognition Platform with Breakout Detection

Pattern recognition Technical setups Breakouts Trend filters Liquidity screening Vectorized detectors Batch reporting Large-universe EOD Reproducible research Python

Marsbridge built a large-universe equities research platform that ingests multi-exchange EOD data and detects priority technical setups with configurable quality rules and optional trend/volume confirmations. We implemented vectorized detectors, practical liquidity screening, and batch PDF reporting.

Customer

Client Private Quantitative Investor (Switzerland)
Industry Systematic Equities
Region Switzerland
Client since 2022

The client sought a repeatable way to surface high-quality technical patterns across broad equity universes, replacing manual scanning with parameterized detectors and audit-ready outputs (CSV/PDF) for daily decision-making.

Challenge

From Manual Charts to Systematic Detection

Detecting complex chart structures over very large symbol sets within practical overnight windows—fast enough for daily use. Encode pattern quality while allowing adjustable tolerance for research exploration.

Solution

Vectorized Pattern Detection Platform

A small, cross-functional squad—Quant Lead, Data Engineer, Research Engineer, Analyst—built the data plane, implemented vectorized pattern detectors, and delivered reviewer-friendly artifacts for daily research.

Multi-exchange EOD data foundation

Multi-exchange EOD data foundation

Consolidated symbols across exchanges with daily refresh and symbol hygiene; standardized time-series panels for detectors and reporting.

Detector family (parameterized)

Detector family (parameterized)

Reversal patterns with geometry rules and configurable spacing/depth. Consolidation patterns with parallelism and touch-count checks. Breakout patterns with optional trend/volume filters to reduce counter-trend triggers.

Liquidity screening

Liquidity screening

Pre-filter step to down-rank or remove illiquid artifacts before detection, improving realism and review throughput.

Performance engineering & reporting

Performance engineering & reporting

Vectorized computation enabled full-universe daily runs. Analyst-ready outputs: Ranked CSVs and multi-section PDFs with overlaid patterns for quick QA and parameter tuning.

Technologies & tools

Programming Languages

Python, NumPy, Pandas

Detection

Vectorized pattern detectors, Chart renderers

Data Sources

Multi-exchange EOD equities, Universe management, Liquidity screening

Reporting

CSV exporters, PDF chart books

Process

Kickoff & data plane—EOD ingest, symbol hygiene, baseline scanners. Detector V1—core reversal patterns + PDFs for feedback. Scale-up—extend to broader universes; vectorize logic. Breakout module—consolidation rules, trend/volume filters. Reporting & handover—batch PDFs/CSVs, runbooks, parameter defaults.

  1. Kickoff & data plane
  2. Detector V1
  3. Scale-up
  4. Breakout module
  5. Reporting & handover

Team

User Icon
1
Quant Lead
User Icon
1
Data Engineer
User Icon
1
Research Engineer
Marsbridge quant research team analyzing patterns

Results

Daily-scale pattern surfacing across broad universes with tunable geometry and validation artifacts. Reproducible research through ranked CSVs and PDFs that replaced manual chart trawling. Higher signal quality via liquidity screening and optional trend/volume filters.

Turn Chart Ideas into Measurable Signals

Have pattern ideas but inconsistent discovery? We convert them into vectorized detectors with reviewer-ready PDFs and ranked lists—so your research scales beyond a handful of charts.

Request a Consultation

Drop us a line! We are here to answer your questions within 1 business day.

What happens next?

1

Once we’ve received and processed your request, we’ll get back to you to detail your project needs and generally sign an NDA to ensure confidentiality.

2

After examining your project requirements, our team will devise a proposal with the scope of work, team size, time, and cost estimates.

3

We’ll arrange a meeting with you to discuss the offer and nail down the details.

4

Finally, we’ll sign a contract and start working on your project with agreed timeline