Quant.Platform Logo
Quant.PlatformQuantitative Systems by Neo-Nix
Wave 5 Supervised Golden Acceptance: PASS|Zero Lookahead Invariant

Deterministic Research.
Causal Trading Architecture.
Provable Alpha.

Most backtests lie because of subtle lookahead leakage, floating-point rounding drift, and naive fill assumptions.Quant.Platform (engineered by Neo-Nix) builds institutional-grade quantitative systems where every hypothesis is verified against monotonic causality, double-entry ledgers, and purged out-of-sample lockboxes.

Temporal Invariant
t_avail ≤ t_dec
Zero lookahead or future-leakage guarantee
Accounting Engine
Decimal (H04)
Double-entry exact ledger, zero float drift
Execution Separation
DecisionIntent
Alpha policies decoupled from execution state
Acceptance Gate
Golden E2E PASS
Verified on Bybit BTCUSDT tick-level data
The Target Architecture

A Causal Multi-Tier Pipeline

From raw uncompressed exchange feeds to deterministically reconciled double-entry equity. Each layer operates behind frozen contract interfaces, preventing semantic bleed.

Tier 01Data Plane

DataGateway

Catalog-backed reader over partitioned Parquet storage. Monotonic timestamp cursor enforcing publication-delay floors.

`DataGateway.scan()`
Tier 02Features

Feature Registry

Strict point-in-time materialization. Eliminates forward-looking rolling calculations and normalizes continuous market states.

`FeatureSetDefinition`
Tier 03Intelligence

Policy Layer

Rule-based alphas, Supervised ML (Wave 5), and Causal RL policies (RFC #183). Generates typed intent without order book coupling.

`DecisionIntent`
Tier 04Replay H01

Order Engine

Deterministic matching simulator. Applies realistic spreads, order book queues, slippage models, and exchange maker/taker fee tiers.

`ReplayEngine`
Tier 05Ledger H04

Double-Entry Core

Exact fixed-scale Decimal accounting. Immutable transaction journals preserving capital conservation laws down to fractional ticks.

`LedgerEntry (Decimal)`
!

The Fundamental Design Constraint

Alpha models cannot execute trades directly; Execution engines cannot modify alpha parameters; Ledgers cannot fabricate capital. All state mutations follow deterministic finite state machine (FSM) rules verified in CI.

Research Methodology

The 5 Invariants of Causal Research

Over 90% of quantitative strategies fail when deployed live because academic backtests rely on unrealistic assumptions. In our lab, every research experiment must satisfy five non-negotiable invariants before capital consideration.

01

Strict Temporal Causality

t_available ≤ t_decision

No strategy can observe a price, candle close, or indicator until its broadcast timestamp has elapsed in real time. We strictly reject synthetic or forward-looking price arrays.

02

Purged & Embargoed Cross-Validation

Lopez de Prado Protocol

Financial time-series possess long-memory serial autocorrelation. Standard k-fold cross-validation leaks information. We enforce temporal purge windows and post-trade embargoes between splits.

03

Exact Double-Entry Accounting

Zero Floating-Point Drift

`float` arithmetic silently introduces compounding rounding errors over millions of simulated trades. Every fill, balance debit, and fee deduction is recorded using fixed-scale `Decimal` double-entry ledgering.

04

Frictional Reality & Fee Hurdle

Maker/Taker & Queue Delay

Mid-price fills are an illusion. Orders are matched against real simulated book depth, factoring in maker rebates, taker penalties, queue priorities, and market impact slippage curves.

05

Out-of-Sample Lockbox

Anti-P-Hacking Protocol

Tuning parameters until a curve looks pretty guarantees overfitting. Final model performance is verified once and once only on a cryptographically sealed lockbox partition of unseen market history.

∞

Reproducible Provenance

Git Commit × Data Hash

Every backtest result records the exact commit hash, raw dataset SHA-256 fingerprint, seed, and environment dependencies for total determinism.

Empirical Studies

Research Tear Sheets & Case Studies

Quantitative hypotheses tested under audited institutional constraints. All metrics account for exchange fees, realistic slippage, and temporal lockbox verification.

Environment:Bybit BTCUSDT Tick / ReplayEngine
Wave 5 Golden PathProduction Verified

Study 01: Causal Supervised ML on BTC

Multi-horizon volatility and momentum projections using strictly causal point-in-time features. Evaluated via purged walk-forward cross-validation with an untouched out-of-sample lockbox.

Sharpe Ratio
1.84
Max Drawdown
-8.4%
Deflated Sharpe
p < 0.01
Cumulative Equity Curve (Out-of-Sample)+34.2%
Contract: `I03, I04, I05`Golden E2E PR #180 →
Wave 4 StrategyDeterministic Replay

Study 02: Multi-Regime Volatility Breakout

Time-series momentum with regime-conditioned volatility filters and dynamic ATR position sizing. Formulated as a pure `StrategySpec` producing `DecisionIntent` actions.

Profit Factor
1.92
Calmar Ratio
2.15
Win Rate
46.8%
Cumulative Equity Curve (Historical Replay)+41.6%
Contract: `G01-G04, H01-H05`Replay PR #161 →
MicrostructureTick-Level Evidence

Study 03: Order Flow Imbalance & VPIN

Measuring volume-synchronized probability of toxicity (VPIN) and order book queue asymmetry across L2/L3 feeds to minimize execution impact slippage.

Spread Capture
68.2%
Slippage Saved
1.8 bps
Queue Fill Rate
91.4%
Target: `Execution Policy`RFC #184 Footprint →
Research FrontierGymnasium Specification

Study 04: Causal RL in Gymnasium

Adapting legacy RL concepts (`ml_core` EnvFlex / FSMExecution) into an audited Gymnasium environment evaluating multi-objective rewards on double-entry replay ledgers.

Framework
Gymnasium
State Machine
FSM Intent
Reward Design
PnL - DD - Fee
Capability: `I06 Strategic RL`RFC #183 Discussion →
Systems Engineering

Built with Institutional Rigor

Trading algorithms are only as robust as the systems running them. We apply strict software engineering disciplines to financial data infrastructure.

01 / Foundation

Type Safety

Zero untyped code. Full strict typing across Python 3.12+, Pydantic v2 schemas, and immutable dataclasses with static verification in CI.

02 / Storage

Parquet & Arrow

Columnar partitioned storage with Snappy/ZSTD compression. Zero row-by-row parsing overhead; sub-millisecond scans over multi-gigabyte tick datasets.

03 / Governance

ADR Architecture

Every contract evolution, fee formula, and gap remediation requires an Architectural Decision Record (ADR) reviewed against frozen baseline specs.

04 / Testing

Golden E2E Gates

Adversarial suites (A1–A9), Golden Bybit BTCUSDT end-to-end integration tests, and ledger balance conservation checked on every PR.