Paper: arXiv 2510.05475
Authors: Fabio Bagarello, Francesco Gargano, Polina Khrennikova
Abstract
We consider state of the art applications of artificial intelligence (AI) in modelling human financial expectations and explore the potential of quantum logic to drive future advancements in this field. This analysis highlights the application of machine learning techniques, including reinforcement learning and deep neural networks, in financial statement analysis, algorithmic trading, portfolio management, and robo-advisory services. We further discuss the emergence and progress of quantum machine learning (QML) and advocate for broader exploration of the advantages provided by quantum-inspired neural networks.
Complexity vs Empirical Score
- Math Complexity: 7.5/10
- Empirical Rigor: 2.0/10
- Quadrant: Lab Rats — high math complexity, limited empirical testing
Why this score: The paper explores advanced mathematical frameworks like quantum logic and quantum machine learning, indicating high theoretical density, but lacks empirical components such as backtests, datasets, or statistical results, placing it in the theoretical research category.
Research Flowchart
flowchart TD R["Research Goal:<br>Explore AI in Financial Expectations<br>& Quantum Logic Potential"] D["Data & Inputs:<br>Financial Statements<br>Market Data<br>Human Expectation Models"] M["Methodology:<br>Classical ML (RL, DNN)<br>+ Quantum ML Analysis"] C["Computational Processes:<br>Simulation & Comparative<br>Modeling of Financial Systems"] F1["Outcome 1:<br>RL & DNN Enhance<br>Trading & Portfolio Mgmt"] F2["Outcome 2:<br>Quantum Logic Offers<br>New Frontiers for Contextual AI"] R --> D D --> M M --> C C --> F1 C --> F2
Evidence Card
What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card
Proposes
The paper proposes the adoption of quantum‑driven AI techniques, such as quantum neural networks and quantum reinforcement learning, to improve upon classical models in capturing human‑like decision‑making in finance.
Source sentence
Ultimately, we aim to promote the adoption of quantum-driven AI techniques to improve upon classical models in capturing human-like decision-making.
Assumes 3
- Human financial expectations exhibit bounded rationality that can be captured by quantum logic. model
Source sentence
These benefits arise from quantum logic’s ability to capture agents’ non-classical expectations and non-expected utility decisions, often referred to as bounded rationality.
- Quantum probability theory provides a valid framework for modeling expectation formation in asset trading. model
Source sentence
The phenomenon of indeterminism and coexistence is formally coined in quantum theory as superposition of states, and can well explain the ‘boundedly rational’ expec-tations about the future states of economy, expected dividends and prices of financial assets, as discussed in quantum probability frameworks of asset trading by e.g., [4]-[5], [32], [45]-[46].
- AI algorithms can be trained in noisy, highly uncertain contexts where black‑swans may occur. data
Source sentence
Furthermore, these AI algorithms may be trained in noisy, highly uncertain contexts where ‘black swan’ events are possible, such as unfore-seen volatility shocks.
Data
No dataset named in the text.
Costs
Not applicable
Finds 3
- Quantum probability‑based models can explain heterogeneous investor beliefs and trading behaviours that deviate from rational‑expectations equilibrium. theoretical
Source sentence
As shown in [46], the quantum probability-based models can explain the trading behaviours of in-vestors, who exhibit heterogeneous beliefs and hence can ‘agree to disagree on the future states of financial variables’.
- Hybrid quantum neural networks (QNNs) implemented for forecasting Chinese stock index prices show performance gains over classical baselines. performance
Source sentence
Hybrid QNNs based on variational quan-tum circuits have been implemented by [72] for forecasting stock index prices within the Chinese stock market, with evidence of performance gains over classical baselines.
- Quantum‑enhanced reinforcement learning (QRL) offers a principled way to encode investors’ risk‑sensitive preferences and adapt sequential allocation strategies to evolving market conditions. theoretical
Source sentence
Quantum-enhanced reinforcement learning (QRL) offers a principled approach to encod-ing investors’ risk-sensitive preferences and learning sequential allocation strategies that adapt to evolving market conditions and partial observability.
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 14 related papers). Coverage is partial, so this is neither replication nor refutation.
Code
No repository by the authors found in the paper.
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.