Skip to content
View fdtorre07-sys's full-sized avatar

Block or report fdtorre07-sys

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
fdtorre07-sys/README.md

Fernando De La Torre

Research-first quant infrastructure focused on validation, provenance, risk gates, and fail-closed trading safety.

Current Focus

  • Research platform: multi-asset allocation, options volatility, intraday alpha, VaR/CVaR, execution costs, provenance labeling, and self-contained HTML reports.
  • Validation harness: chronological out-of-sample testing that separates command success from research success.
  • Safety lab: synthetic fail-closed signal intake, paper evidence ledgers, provenance gates, and explicit research/paper/real-money boundaries.

Public Repos

Evidence Demos

  • Reviewer proof pack: one-page audit map and resume bullets.
  • Failure as a feature: walk-forward-validation-harness intentionally returns research_verdict: FAIL to prove weak signals are rejected.
  • Fail-closed safety: trading-safety-lab intentionally returns safety verdict BLOCK while the demo command exits successfully.
  • Provenance labels: institutional-quant-platform labels synthetic fallback data and source stamps instead of implying a live track record.
  • Survivorship honesty: institutional-quant-platform documents fixed current-universe limitations instead of claiming delisted-asset coverage.
  • Risk gates: validation, cost stress, concentration checks, and paper/live boundaries are treated as product surfaces, not footnotes.

What This Is Not

This is not a profit claim, not investment advice, and not a live trading bot. The work is research infrastructure: paper/sim first, no broker execution path, no hidden track record, no survivorship-free alpha claim, and no capital deployment without explicit gates and evidence.

Pinned Loading

  1. institutional-quant-platform institutional-quant-platform Public

    Institutional-style quant research stack with risk, options, allocation, provenance, tests, and HTML reporting.

    Python

  2. walk-forward-validation-harness walk-forward-validation-harness Public

    Synthetic walk-forward validation harness that intentionally returns FAIL to reject brittle signals before capital deployment.

    JavaScript

  3. trading-safety-lab trading-safety-lab Public

    Synthetic fail-closed safety-gate demo for paper/sim research infrastructure; no execution UI.

    JavaScript

  4. fail-closed-execution-gateway fail-closed-execution-gateway Public

    Synthetic fail-closed execution gateway for paper/live boundary, risk gates, and human confirmation checks.

    JavaScript