A Quantum Neural Network Approach for Portfolio Selection

R.P Mahajan

A new field of computation is emerging which integrates quantum and classical computation.This is applied to solve the financial engineering problem of portfolio selection.Hopfield neural network is used for portfolio selection.A quantum inspired hybrid model of quantum neurons and classical neurons is proposed for the prediction of stock prices.An effort is made, probably the first time to develop and use a hybrid quantum neural network for the prediction of stock prices.The suggested multilayer hybrid quantum neural network contains hidden layer of quantum neurons while the visible layer is of classical neurons.The asset distribution is done by a modified greedy algorithm.It is assumed that quantum computers when come into existence shall provide huge potential in the form of computational power and memory.Classical Neural networks(CNN) have shown tremendous acceptability in solving problems with non-linear formulations that requires huge processing power and large memory which a quantum computer can provide, when they will come into existence.

SONALI V. BHARAD, Sanjay R. Sutar, Arun R. Babhulgaonkar +1 more

Atharva Indulkar

Current quantum portfolio optimization pipelines rely on Random Matrix Theory (RMT) forcorrelation matrix cleaning, a static linear method that cannot adapt when market regimesshift. Meanwhile, D-Wave's own operational audit shows the quantum processor runs for just0.68% of total computation time, with input quality driving all output quality essentially. Thispaper proposes using Quantum Neural Networks (QNNs) — or, as a near-term fallback,classical neural networks — as an adaptive preprocessing layer before quantum portfoliooptimization. QNNs offer provable universal approximation guarantees, non-linear correlationmodeling, and regime-aware adaptation. Combined with quantum annealing or gate-modelVariational Quantum Eigensolvers (VQE/QAOA) for the actual allocation step, this creates atwo-stage pipeline where better inputs lead to meaningfully better portfolios. We present themathematical foundations, compare the approach against RMT, discuss hardware-awaredesign trade-offs, and outline what can be built today on standard hardware.

Narun Tripathi Narun, Divyata Sain, Harishita +2 more

Bahadur Yadav, Sanjay Kumar Mohanty

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.

Michael Marzec