Skip to content
Blackshore Agency

Work/Finance

A research platform that lets the analysts do research

Data pipelines, distributed compute and reproducible backtesting for a quantitative research team.

Client
A quantitative hedge fund
Sector
Finance
Capability
Automation & AI

Technology

  • Python
  • NumPy
  • pandas
  • numba
  • Ray
  • Dagster
  • JupyterHub
  • MLflow
  • ClickHouse
  • Kubernetes
  • S3

The challenge

Analysts spent more of their week cleaning data and maintaining scripts than testing ideas, and results were hard to reproduce from one researcher to the next.

Our approach

  1. 01Built reliable, versioned pipelines for market and alternative data
  2. 02Standardized the research and backtesting toolkit across the team
  3. 03Made every result reproducible from its data, code and parameters

The engineering

Pipelines with contracts

Orchestrated ingestion of market, fundamental and alternative data, each feed validated against a schema and statistical checks before it reaches research. Datasets are versioned, so any past result can be re-run on exactly the data it saw.

A shared research library

A common library of signals, factor definitions, transaction-cost models and vectorized backtests, compiled with numba where speed matters, so every analyst builds on the same tested foundations.

Compute on demand

Parameter sweeps, walk-forward validation and model training fan out across a cluster and scale back to zero when idle, turning overnight jobs into minutes.

Machine learning and language models

Models trained on alternative data with strict separation of training and test periods, and language models that extract structured signals from filings and transcripts, each extraction reviewable by a person.

The outcome

Research moves from question to answer faster, and every result can be traced, repeated and trusted.

Also within reach

Everything a fund's technology runs on.

  • 01

    Research platforms

    Point-in-time data, factor libraries, vectorized and event-driven backtesting, and distributed parameter search with walk-forward validation.

  • 02

    Execution and order management

    Broker and exchange connectivity over FIX and native APIs, execution algorithms, pre-trade risk and a complete audit trail of every order.

  • 03

    Risk and portfolio analytics

    Exposure, attribution, scenario and stress testing, and real-time P&L consolidated across books, custodians and currencies.

  • 04

    Machine learning and AI

    Models on market and alternative data, and language models that read filings, transcripts and research with human review.

  • 05

    Data engineering

    Market, fundamental and alternative data pipelines with validation, lineage and versioned datasets that make every result reproducible.

  • 06

    Investor and principal reporting

    Secure portals and automated reporting for investors, principals and family members, built on the same numbers the desk trades on.