Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Evaluating Hybrid Quantum – Classical Models for Financial Market Prediction in the NISQ Era

Neelesh Kumar, Manisha Devi, Dr.Rashmi gupta, Shivani Sharma

Published Jan 1, 2026• 0 citations
Publisher
DOI
10.2139/ssrn.7186258

Related papers

Hybrid Quantum Deep Learning for Financial Market Trend Prediction

Rajat Kumar Dwibedi, L. K. Hema, Dhinil V Dhinesh +3 more

International Conference on IoT, Communication and Automation Technology (ICICAT)•Dec 5, 2025•0 citations

QUANTUM PROBABILISTIC MODEL FOR THE FINANCIAL MARKET

Olga Choustova

Quantum Probability and Infinite Dimensional Analysis•Jul 1, 2007•1 citation

Quantum Computing Approaches to Portfolio Optimization Under Risk and Market Uncertainty

Oğuzhan Günal

Portfolio optimization under conditions of risk and market uncertainty remains a foundational challenge in financial economics and investment management. Classical optimization frameworks, including mean–variance models and stochastic programming approaches, often struggle with high-dimensional asset universes, nonlinear correlations, and dynamic market regimes. This paper examines quantum computing approaches to portfolio optimization under risk and market uncertainty, focusing on hybrid quantum–classical algorithms designed to enhance combinatorial optimization and probabilistic modeling. By integrating quantum annealing, variational quantum circuits, and quantum-enhanced sampling techniques with classical financial analytics, the study evaluates their potential to improve computational efficiency and scenario sensitivity. The analysis considers both theoretical advantages and practical limitations within the Noisy Intermediate-Scale Quantum (NISQ) era. The findings suggest that quantum-assisted optimization may complement traditional portfolio models by expanding feasible solution spaces and improving robustness under uncertainty, thereby contributing to more adaptive and resilient investment strategies.

Next generation.•Mar 4, 2026•0 citations

Quantum-Assisted Time Series Modelling for Volatility Prediction in Indian Stock Indices

M. Sriram, NAGESH B

Financial risk management faces the essential problem of forecasting stock market volatility because traditional econometric models including GARCH fail to demonstrate the complex market behavior which characterizes emerging markets. The research investigates how quantum computing functions as an innovative forecasting method through its assessment of actual volatility patterns observed in four primary Indian stock market indexes between 2015 and 2025. Researchers tested two hybrid quantum-classical systems which included a Variational Quantum Regressor (VQR) and a Quantum Kernel Support Vector Regression (QK-SVR) against traditional GARCH family models and Long Short-Term Memory (LSTM) networks. The results demonstrate that quantum-assisted models achieve better performance than both traditional methods and deep learning benchmarks throughout all market scenarios while maintaining stability during financial emergencies. The VQR model which included India VIX data achieved maximum performance because it decreased Root Mean Square Error (RMSE) by 90% when compared to GARCH and by 65% to 76% when measured against LSTM. The current Noisy Intermediate-Scale Quantum (NISQ) era allows hybrid quantum models to function as efficient and accurate forecasting instruments for emerging market predictions.

International Academic Research Journal of Business and Management•May 4, 2026•0 citations

Quantum Computing Models for Financial Analysis

Pablo Herrero-Gómez, Francisco A. Pujol, Ana Martinez García +1 more

Lecture notes in networks and systems•Jan 1, 2026•1 citation

Scenario-Based Macroeconomic and Financial Forecasting Using Quantum-Enhanced Models

Oğuzhan Günal

Macroeconomic and financial forecasting plays a central role in policy design, risk management, and capital allocation, yet traditional econometric and machine learning models often struggle with nonlinear dynamics, structural breaks, and high-dimensional uncertainty. This paper explores scenario-based macroeconomic and financial forecasting using quantum-enhanced models, examining how hybrid quantum–classical frameworks can improve predictive performance under complex and volatile conditions. By integrating quantum optimization, probabilistic sampling, and high-dimensional feature mapping with scenario analysis techniques, the study proposes an architecture for modeling systemic risk, regime shifts, and tail-event dynamics. The analysis evaluates theoretical advantages, computational constraints, and implementation challenges within the Noisy Intermediate-Scale Quantum (NISQ) era. The findings suggest that quantum-enhanced forecasting may complement classical approaches by expanding solution space exploration and enhancing scenario sensitivity, thereby contributing to more resilient macro-financial decision-making systems.

Next generation.•Mar 4, 2026•0 citations
Portfolio optimization under conditions of risk and market uncertainty remains a foundational challenge in financial economics and investment management. Classical optimization frameworks, including mean–variance models and stochastic programming approaches, often struggle with high-dimensional asset universes, nonlinear correlations, and dynamic market regimes. This paper examines quantum computing approaches to portfolio optimization under risk and market uncertainty, focusing on hybrid quantum–classical algorithms designed to enhance combinatorial optimization and probabilistic modeling. By integrating quantum annealing, variational quantum circuits, and quantum-enhanced sampling techniques with classical financial analytics, the study evaluates their potential to improve computational efficiency and scenario sensitivity. The analysis considers both theoretical advantages and practical limitations within the Noisy Intermediate-Scale Quantum (NISQ) era. The findings suggest that quantum-assisted optimization may complement traditional portfolio models by expanding feasible solution spaces and improving robustness under uncertainty, thereby contributing to more adaptive and resilient investment strategies.
Financial risk management faces the essential problem of forecasting stock market volatility because traditional econometric models including GARCH fail to demonstrate the complex market behavior which characterizes emerging markets. The research investigates how quantum computing functions as an innovative forecasting method through its assessment of actual volatility patterns observed in four primary Indian stock market indexes between 2015 and 2025. Researchers tested two hybrid quantum-classical systems which included a Variational Quantum Regressor (VQR) and a Quantum Kernel Support Vector Regression (QK-SVR) against traditional GARCH family models and Long Short-Term Memory (LSTM) networks. The results demonstrate that quantum-assisted models achieve better performance than both traditional methods and deep learning benchmarks throughout all market scenarios while maintaining stability during financial emergencies. The VQR model which included India VIX data achieved maximum performance because it decreased Root Mean Square Error (RMSE) by 90% when compared to GARCH and by 65% to 76% when measured against LSTM. The current Noisy Intermediate-Scale Quantum (NISQ) era allows hybrid quantum models to function as efficient and accurate forecasting instruments for emerging market predictions.
Macroeconomic and financial forecasting plays a central role in policy design, risk management, and capital allocation, yet traditional econometric and machine learning models often struggle with nonlinear dynamics, structural breaks, and high-dimensional uncertainty. This paper explores scenario-based macroeconomic and financial forecasting using quantum-enhanced models, examining how hybrid quantum–classical frameworks can improve predictive performance under complex and volatile conditions. By integrating quantum optimization, probabilistic sampling, and high-dimensional feature mapping with scenario analysis techniques, the study proposes an architecture for modeling systemic risk, regime shifts, and tail-event dynamics. The analysis evaluates theoretical advantages, computational constraints, and implementation challenges within the Noisy Intermediate-Scale Quantum (NISQ) era. The findings suggest that quantum-enhanced forecasting may complement classical approaches by expanding solution space exploration and enhancing scenario sensitivity, thereby contributing to more resilient macro-financial decision-making systems.