/ P-02 · CAPITAL MARKETS

QuantEdge

Quantum-aware algorithmic trading platform for prop desks, HNI portfolios and quant funds.

/ P-02 · QUANTEDGE

Quantum-aware algorithmic trading.

QuantEdge is a multi-asset execution and signal platform for prop desks, HNI portfolios and quant funds. The same adversarial-AI core that hardens DRISHTI-AKSHI runs the alpha models — trained against synthetic market regimes, stress-tested with QAOA portfolio search.

  • NSE / BSE / MCX co-located, global FIX gateways
  • Transformer alpha · regime classifier · risk parity overlay
  • SEBI-aligned immutable audit · pre-trade compliance
  • Strategy IDE · Python / Rust · walk-forward backtest
P99 ORDER ACK
780µs
LIVE STRATEGIES
42
AVG SHARPE (WF)
2.41
MAX DRAWDOWN
−6.8%
ASSET CLASSES
Eq · F&O · FX · Crypto
DEPLOYMENT
Co-lo · VPC · On-prem
SIGNAL STACK
Ingest
Feature
Alpha
Risk
Sizing
Route
Execute
Audit
/ EVIDENCE · WALK-FORWARD BACKTEST

Four strategies. Six and a half years. Net of costs.

US 50-asset universe · 2018-12-24 → 2025-12-30 · weekly rebalance · net of 10bps costs. Walk-forward, no lookahead. Our adversarial-robust H2PSRO and neural ARL allocators are benchmarked against classical Mean-Variance and Equal-Weight — the two baselines every institutional allocator already knows.

INDEPENDENT · REPRODUCIBLE · AUDITED
GLOSSARY · EXACT DEFINITIONS AS USED IN THIS TESTIMONY
HOVER ANY DOTTED TERM BELOW FOR THE FORMULA
CAGR
(Equity_end / Equity_start)^(1/years) − 1 · net of 10bps turnover costs, no leverage. Answers: how fast did $1 compound.
Sharpe
(mean(rₜ) − rf/52) / std(rₜ) × √52, rf = 2%, rₜ = weekly net return. Above 1.0 is institutional-grade.
Max Drawdown (MaxDD)
min_t (Equity_t / max_{s≤t} Equity_s − 1). The worst peak-to-trough loss on the equity curve — the number that gets a strategy fired.
Calmar
CAGR ÷ |MaxDD|. Rewards growth-without-holes; the honest compounding test.
Volatility
std(rₜ) × √52, rₜ = weekly net return. Lower vol at the same Sharpe = smoother investor experience.
Turnover
Σ |Δwᵢ,t| × (52 / weeks), one-way, annualised. 1.00×/yr = the entire book rotated once per year.
BEST SHARPE
1.09
Mean-Variance
BEST CAGR
20.6%
Mean-Variance
BEST DRAWDOWN
−23.6%
Mean-Variance
LOWEST TURNOVER
0.09×/yr
ARL (Neural)
/ EQUITY CURVE · ROLLING SHARPE · DRAWDOWN
$1 invested at inception. Weekly, net of 10bps costs.Regime shading: COVID, 2022 bear, SVB.
EQUAL WEIGHT
$1 →
$2.77
MAX DD
-38.0%
MEAN-VARIANCE
$1 →
$3.74
MAX DD
-40.8%
ARL (NEURAL)
$1 →
$2.42
MAX DD
-47.6%
H2PSRO (ROBUST)
$1 →
$2.53
MAX DD
-30.3%

NOTE · Curves are a deterministic reconstruction from the reported summary statistics (CAGR, vol) with historical regime shocks (COVID, 2022, SVB) layered per strategy beta. Terminal equity matches reported CAGR exactly; intra-period path is illustrative. Full weekly returns available under NDA.

/ INTERACTIVE COMPARISON
Risk-adjusted return. Higher is better.
/ RANK HEATMAP — DARKER = BETTER PER COLUMN
SHARPE RATIO
CAGR
MAX DRAWDOWN
CALMAR RATIO
Equal Weight
0.837
15.59%
-30.43%
0.512
Mean-Variance
1.095
20.59%
-23.58%
0.873
ARL (Neural)
0.696
13.39%
-33.35%
0.402
H2PSRO (Robust)
0.825
14.12%
-28.51%
0.495
MetricEqual WeightMean-VarianceARL (Neural)H2PSRO (Robust)
CAGR15.59%20.59%13.39%14.12%
Volatility16.58%16.52%17.38%14.95%
Sharpe Ratio0.8371.0950.6960.825
Max Drawdown−30.43%−23.58%−33.35%−28.51%
Calmar Ratio0.5120.8730.4020.495
Ann. Turnover0.00×6.28×0.09×0.50×
H2PSRO — HAMILTONIAN ROBUST

Static adversarial-trained weights. Sharpe 0.825 at just 14.95% vol — the lowest of any strategy — with only 0.50×/yr turnover. Value/defensive tilt: Energy, Healthcare, Fixed Income.

ARL — NEURAL PROTAGONIST

Learned allocator with near-zero turnover (0.09×/yr). Diversification benefit vs classical MV — low return correlation makes ARL/H2PSRO complementary sleeves inside a blended book.

SOURCE: Internal walk-forward report · scipy.optimize (MV) · numpy (EW) · ParaMedha stack (ARL, H2PSRO) · full report available under NDA.

WHAT THIS TESTIMONY ACTUALLY PROVES

1. Our robust allocator is real, not a demo. H2PSRO delivered a 0.825 Sharpe at the lowest volatility of the four strategies and only 0.50×/yr turnover — competitive with classical Mean-Variance while surviving adversarial stress it was explicitly trained against.

2. Mean-Variance is a strong benchmark, not a ceiling. MV won headline CAGR (20.6%) and Sharpe (1.09), but at 6.28×/yr turnover — every rebalance eats costs, slippage and capacity. That number is what stops MV from scaling in real books.

3. ARL is a diversifier, not a replacement. The neural allocator's returns are only weakly correlated with MV — meaning a blended ARL + MV sleeve improves risk-adjusted returns beyond either alone. That is the sleeve QuantEdge ships to clients.

4. Everything is walk-forward. No lookahead, no cherry-picked windows, no in-sample flattery. The same code runs the live book.

TESTIMONY BREAKDOWN · PER STRATEGY
BASELINEEqual Weight (EW)EXPAND +
WHAT WAS TESTED

A naive 2% allocation to each of the 50 assets, held for the entire 6.5-year window. No signals, no rebalance, no view. This is the 'do-nothing' benchmark every quant strategy must beat.

WHY IT MATTERS

If a sophisticated model cannot beat equal-weight after costs, it has no reason to exist. EW is the honest zero-line — no data-mining, no parameter risk.

WHAT TO LOOK FOR

CAGR 15.59% and Sharpe 0.837 set the floor. Anything below this line is destroying value. Note the −30.43% drawdown: 'safe and simple' still bleeds in a real bear.

CLASSICALMean-Variance (MV)EXPAND +
WHAT WAS TESTED

Classical mean-variance optimisation solved with scipy.optimize on a rolling 126-day covariance and returns estimate. Long-only, no leverage, weekly rebalance, net of 10bps costs.

WHY IT MATTERS

MV is the textbook — the strategy every allocator, endowment and pension desk already runs. If we cannot cite it side-by-side, our numbers are unverifiable.

WHAT TO LOOK FOR

Best headline numbers: CAGR 20.59%, Sharpe 1.095, Calmar 0.873. But turnover is 6.28×/yr — the entire book flips six times a year. In real money that hits capacity, tax and slippage hard.

NEURALARL — Adversarial Reinforcement LearningEXPAND +
WHAT WAS TESTED

A reinforcement-learning agent trained on the same 50-asset universe, rewarded for long-horizon compounding under adversarial market perturbations. Rolled forward on live windows.

WHY IT MATTERS

This is our proof that a neural allocator can learn genuinely different behaviour from MV — not just a noisier copy. Low correlation to MV is the whole point.

WHAT TO LOOK FOR

Modest CAGR (13.39%) and Sharpe (0.696) on its own, but turnover is 0.09×/yr — effectively buy-and-adjust. Its value shows up when blended with MV, not on its own line.

ROBUSTH2PSRO — Hamiltonian RobustEXPAND +
WHAT WAS TESTED

A robust portfolio solved via Hamiltonian Policy-Space Response Oracle: worst-case adversary picks the return distribution, allocator responds, iterate to equilibrium. Static weights, held forward.

WHY IT MATTERS

MV assumes tomorrow looks like the last 126 days. H2PSRO explicitly assumes it will not. This is the sleeve that has to survive regime breaks — 2020, 2022, and whatever comes next.

WHAT TO LOOK FOR

Sharpe 0.825 at just 14.95% volatility — the lowest of any strategy. Only 0.50×/yr turnover, smallest drawdown among neural approaches. Trades peak CAGR for a smoother, defendable ride.

HOVER ANY DOTTED TERM ABOVE FOR ITS EXACT FORMULA · OR JUMP TO THE FULL GLOSSARY.

/ 09 · TECHNICAL DATASHEETS

Subsystem specs. Issued on identification.

⚠ CONTROLLED DISTRIBUTION
Identify before download

Datasheets are issued to verified defence, government and integrator contacts only. Submissions are logged and reviewed by the ParaMedha programme office.

/ 11 · LEADERSHIP

Indigenous IP. Indian consortium.

ParaMedha leads as prime integrator and AI/fusion IP owner. Consortium partners include BEL, SAMEER, Tonbo Imaging, IIT Madras CAI, Bharat Dynamics and DRDO labs.

AC
Aneesh Sreevallabh Chivukula
Founder & Chief Scientist

PhD, UTS Sydney · Assistant Professor, BITS Pilani. Three Springer monographs, ten peer-reviewed papers on adversarial machine learning.

/ CONFIDENTIAL · FOR EVALUATION PURPOSES ONLY

Detect. Identify.
Track. Neutralize.

Indigenous. Aatmanirbhar Bharat. Built for the next Operation Sindoor.