arXiv subjects

Bahadur Yadav

Publications and source records attributed to Bahadur Yadav.

5 recordsLinked to original sources

arXiv2026

A Systematic Review of Recent Advancements in PINN Augmented Deep Learning and Mathematical Modeling for Efficient Portfolio Management

In finance, portfolio management is a traditional yet difficult problem that has drawn attention from practitioners and researchers for many years. However, there are still difficult technological problems that need to be solved. In the world of finance, managing a portfolio has never been easy. Selecting portfolios in a volatile market is made easier with the help of portfolio management. The goal of this review study is to present the concept of physics-informed neural networks because they provide a novel approach to directly incorporating physics and finance principles into the neural network's learning process. By doing so, physics-informed neural networks ensure that their forecasts are in line with established financial regulations and processes in addition to offering precise forecasts. Furthermore, this article provides an overview of the current state of research in portfolio optimization with the support of mathematical models, deep learning models and physics-informed neural networks. In addition, the advantages and disadvantages of various deep learning and mathematical modelling are discussed. Researchers and business professionals alike should find the data useful for advancing the field of investment management and trying out new portfolio management strategies. For this purpose, in this review work, emphasis is given to these factors. Finally, a few challenging issues and potential future directions are discussed, encouraging readers to consider fresh ideas in this field of study.

math.OC↗

arXiv2026

Hybrid Quantum-Classical Ridgelet Neural Networks for Portfolio Optimization

In this study, we introduce a quantum computing method that incorporates Ridglet transforms into quantum processing pipelines for financial time-series forecasting with Quantum Approximate Optimization Algorithm (QAOA)-based portfolio optimization. We propose a Quantum Ridgelet Neural Network (QRNN) model for forecasting time-series data that integrates Parametrized Quantum Circuits (PQCs) with ridgelet-based feature transformations and QAOA-based portfolio optimization for asset selection. By breaking down financial time-series data into multi-resolution components, the ridgelet transform enables the identification of both local and global trends. Ridgelet-based features improve the scalability and accuracy of quantum computing by significantly reducing the number of qubits needed. However, the predicted results are turned into a QUBO-based mean-variance optimization problem and solved with QAOA to select the best stocks. Our study begins with a theoretical formulation of the single-qubit system for our proposed model. This formulation is further extended to a multi-qubit system, and we show that it captures a significant fraction of the predictive signal.

cs.LG↗

arXiv2026

A hybrid wavelet-based physics-informed neural network for portfolio management

In this paper, we present a Hybrid Wavelet-based Physics-Informed Neural Networks (HW-PINNs) framework for portfolio management that provides a promising alternative to Physics-Informed Neural Networks (PINNs). Here, we first discuss the generalized framework of the Merton jump diffusion model and the associated HW-PINNs, followed by the one-dimensional case of a European option. Our work adapts the HW-PINN framework to the Merton jump-diffusion model for a European option, using a simplified direct coefficient optimization strategy, a mathematically corrected log-space formulation, and an efficient FFT -based computation of the integro-differential operator. Through numerical experiments across realistic market scenarios, we show that our proposed model achieves high accuracy and robustness, with a mean relative error of 0.27\% in low jump intensity scenarios compared to high-fidelity benchmarks. Our results validate that the implementation of this specific HW-PINN framework is a computationally efficient and reliable tool for pricing derivatives in markets with high jump risk. In addition, we further discuss risk analysis using Value at Risk (VaR) and Conditional Value at Risk (CVaR), which provide insights into downside risk across different market scenarios.

math.OC↗

arXiv2025

Hybrid Ridgelet Deep Neural Networks for Data-Driven Arbitrage Strategies

In this study, we propose a novel model framework that integrates deep neural networks with the Ridgelet Transform. The Ridgelet Transform on Borel measurable functions is used for arbitrage detection on high-dimensional sparse structures. This transform also enhances the expressive power of neural networks, enabling them to capture complex and high-dimensional market structures. Theoretically, we determine profitable trading strategies by optimizing hybrid ridgelet deep neural networks. Further, we emphasize the role of activation functions in ensuring stability and adaptability under uncertainty. We use a high-performance computing cluster for the detection of arbitrage across multiple assets, ensuring scalability, and processing large-scale financial data. Empirical results demonstrate strong profitability across diverse scenarios involving up to 50 assets, with particularly robust performance during periods of market volatility.

math.OC↗

arXiv2025

Encoder Decoder Generative Adversarial Network Model for Stock Market Prediction

Forecasting stock prices remains challenging due to the volatile and non-linear nature of financial markets. Despite the promise of deep learning, issues such as mode collapse, unstable training, and difficulty in capturing temporal and feature level correlations have limited the applications of GANs in this domain. We propose a GRU-based Encoder-Decoder GAN (EDGAN) model that strikes a balance between expressive power and simplicity. The model introduces key innovations such as a temporal decoder with residual connections for precise reconstruction, conditioning on static and dynamic covariates for contextual learning, and a windowing mechanism to capture temporal dynamics. Here, the generator uses a dense encoder-decoder framework with residual GRU blocks. Extensive experiments on diverse stock datasets demonstrate that EDGAN achieves superior forecasting accuracy and training stability, even in volatile markets. It consistently outperforms traditional GAN variants in forecasting accuracy and convergence stability under market conditions.

cs.LG↗