VQLS forecasting
VQLS for Financial Time-Series Forecasting
A variational quantum linear solver applied end to end to next-day stock price forecasting on real market data.
Accepted · SASIGD 2026 (IEEE SSIT, CBIT Hyderabad)
- 2 × 2linear system
Interactive abstract
Play with the idea
This interactive diagram needs JavaScript. The schematic and write-up below explain the same idea.
Layman view
In plain words
Draft — to be verified. Written in plain language from the paper and project notes on this site.
Many forecasting methods come down to solving a system of linear equations. The variational quantum linear solver (VQLS) is a near-term quantum algorithm for exactly that, but it has mostly been shown on made-up test problems.
This project ran VQLS end to end on real data. Daily closing prices of Reliance Industries from January to April 2023 were turned into a small (2 × 2) linear system, solved with quantum circuits on a simulator, and the result was used to forecast the next day's price.
It is an honest test: at this tiny size there is no quantum advantage, and simple classical methods are just as accurate and much faster. The value is in running the whole workflow and showing exactly where it would have to scale.
Expert view
The work, step by step
-
01
Problem
Existing VQLS demonstrations focus on synthetic test cases; practical deployment on domain-specific data remains sparse. The question was whether the quantum-classical hybrid architecture can be validated on an authentic forecasting workflow before hardware scales.
-
02
Approach
A Hankel-like trajectory matrix is built from daily closing prices of Reliance Industries (January to April 2023) and decomposed into a Pauli basis. Hadamard test circuits evaluate the VQLS cost function, COBYLA optimizes the variational parameter with 10,000 shots per circuit, and a SWAP test estimates the overlap of the solution state with recent market data to give the next-day forecast. All circuits run in Qiskit on the Aer simulator.
-
03
Result
The workflow runs end to end on the Aer simulator with shallow circuits (depth ~6) compatible with NISQ hardware, and the solution is verified against AR(1) and linear regression baselines. Quantum advantage is not realized at this 2 × 2 scale, and the classical baselines reach equivalent accuracy in negligible time. The paper identifies the scalability bottlenecks: exponential growth of the Pauli decomposition and COBYLA shot overhead.
-
04
Status
Accepted and presented as a talk and paper at SASIGD 2026 (IEEE SSIT, CBIT Hyderabad); to be available online later.
Schematic
How it works
Contribution
My role
First author.
- Trajectory matrix—
- Pauli decomposition—
- Hadamard-test cost—
- COBYLA optimisation—
- SWAP-test forecast—
Publication
The paper
2026 · Conference paper and talk · Accepted and presented; online later
Variational Quantum Linear Solver for Time Series Forecasting: A Practical Implementation on Financial Data
S. Siyanwal, B. Kape, C. Pushkarna, K. Islur, T. Kumar, N. Khan, K. Dave
SASIGD 2026 (IEEE SSIT, CBIT Hyderabad)
Abstract
A variational quantum linear solver (VQLS) applied to time series forecasting on real financial market data. Hankel-like trajectory matrices are built from historical Reliance Industries stock prices and the resulting linear system is solved with a quantum-classical hybrid approach: Hadamard test circuits evaluate the cost function, COBYLA optimizes the variational parameters, and a SWAP test estimates the overlap of the solution state with recent market data to give the next-day forecast. Quantum advantage is not realized at this problem scale (2 × 2 system), and classical baselines reach equivalent accuracy; the workflow runs end to end on the Aer simulator with shallow circuits (depth ~6) compatible with NISQ hardware, and the paper identifies its scalability bottlenecks.