This is the authors' abstract. We don't add key points for this paper.
This paper uses quantum state coding and quantum-classical hybrid models based on quantum state coding and quantum-classical hybrid models to solve the portfolio optimization problem in real estate project investment. The article transforms classical real estate data, such as house prices and rental yields, into quantum states for processing through quantum state coding methods, and constructs a quantum-classical hybrid model to overcome current quantum hardware limitations. The empirical results show that the average relative error of the quantum machine learning model is 3.26% in terms of investment risk prediction, which demonstrates an obvious advantage compared with the 9.36% error of the traditional support vector machine model. The model also shows good anti-interference ability, and the prediction error can still be kept within 8% after adding noise data. The financial index simulation of a long term rental apartment project shows that the probability of the project’s NPV reaching the expected level is 75.61%, the probability of the payback period meeting the expectation is 86.6%, and the probability of the internal rate of return exceeding the expected value is 47.4%, which provides a quantitative basis for the investment decision. In addition, the analysis of the cash flow of the underlying assets through quantum-enhanced Monte Carlo simulation shows that the probability of the project’s cash flow coverage multiple greater than 1 in the first five years gradually decreases from 79.27% in the first year to 37.74% in the fifth year, which reveals the reimbursement risk of the project in the middle and late stages.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Liu et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: