Quant-IQ

QuantIQ: A Quantum-Enhanced Lead Generation Pipeline for Global Furniture & Equipment Trade

Authors

• Raja Ram M (ORCID) - Zius Quantum R&D Center
• Krypur Quantum R&D (ORCID) - Kryptur OU

Contributors

• Muskan S (ORCID) - Data T Research Org
• Vipul Jain (ORCID) - AE Quantum Research Division
• Kalinga Swain - Zius Quantum R&D Center

Data Manager: Borel Sigma Data Center

Overview

QuantIQ integrates UN Comtrade trade data, GPU-accelerated tensor/graph preprocessing, and NISQ quantum algorithms (QSVM, QAOA, VQE, Grover) to score B2B leads. The pipeline demonstrates quantum advantage on classically hard data (AUC 0.994 vs 0.971) and identifies the PCA bottleneck on real trade features.

Repository Structure

Path	Description
Quantum_Lead_Pipeline.tex	Technical report (LaTeX source)
qpu_stage*.py	Quantum algorithm experiments
qsvm_*.py	Quantum SVM simulations
preprocess_*.py	PCA and feature normalization
figures/	Research visualisations (PNG/GIF)
*.json	QPU experiment results
quantiq_client.py	API client for live scoring

Quick Start

python3 -m venv venv
source venv/bin/activate
pip install pennylane qiskit scikit-learn pandas matplotlib numpy

# Run quantum advantage proof
python qsvm_quantum_advantage_final.py

# Query live API
python quantiq_client.py 10

Build Paper

pdflatex Quantum_Lead_Pipeline.tex
pdflatex Quantum_Lead_Pipeline.tex

Citation

M RR, Krypur Quantum R&D, S M, Jain V, Swain K (2026)
QuantIQ: A Quantum-Enhanced Lead Generation Pipeline for Global Furniture and Equipment Trade.
doi:10.5281/zenodo.20765960

License

Open research materials for public fork and benefit. See repository for data usage terms.