{"paper_id":"2503.15403","title":"HQNN-FSP: A Hybrid Classical-Quantum Neural Network for Regression-Based Financial Stock Market Prediction","authors":["Prashant Kumar Choudhary","Nouhaila Innan","Muhammad Shafique","Rajeev Singh"],"paper_date":"2025-03-19","paper_type":"methodological","paper_url":"https://arxiv.org/pdf/2503.15403v1","page_url":"https://thequant.space/flowcharts/hqnn-fsp-a-hybrid-classical-quantum-neural-network-for-regr/","scores":{"empirical_rigor":3,"math_complexity":7.5,"quadrant":"Lab Rats"},"proposes":{"status":"available","statement":"The paper proposes a hybrid quantum‑classical architecture that integrates custom‑designed QNNs with classical deep learning models (RNN, LSTM, BiLSTM, GRU) for stock market prediction.","quote":"Development of a hybrid quantum-classical architecture: We propose a hybrid model that seamlessly integrates custom-designed QNNs with classical deep learning architectures, including RNNs, LSTMs, BiLSTMs, and GRUs, to enhance predictive performance.","summary":"Financial time-series forecasting remains a challenging task due to complex temporal dependencies and market fluctuations. This study explores the potential of hybrid quantum-classical approaches to assist in financial trend prediction by leveraging quantum resources for improved feature…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Temporal integrity is preserved by splitting the dataset in a time‑ordered manner into training and testing subsets.","type":"data","stated":"implied","quote":"To preserve temporal integrity, the dataset is split in a time-ordered manner into training and testing subsets."},{"assumption":"Feature selection using SelectKBest identifies the most informative inputs for predicting the closing price.","type":"data","stated":"implied","quote":"To achieve this, the SelectKBest method is used to extract the most informative features that best describe the target variable, which, in this case, is the closing price."},{"assumption":"k‑Fold cross‑validation assumes data points are independently and identically distributed.","type":"statistical","stated":"explicit","quote":"The k-Fold Cross-Validation technique randomly divides the dataset into K equal folds, assuming data points are independently and identically distributed."},{"assumption":"Normalization is required because models are sensitive to feature scale variations.","type":"model","stated":"implied","quote":"Since models are sensitive to feature scale variations, an additional normalization step is necessary to"},{"assumption":"Technical indicators (RSI, MACD, ADX) improve feature representation for market dynamics.","type":"market","stated":"implied","quote":"The integration of these technical indicators enriches the dataset, facilitating a more robust analysis of market dynamics."}]},"datasets":{"status":"available","items":[{"name":"historical stock prices","provider":null,"kind":"market-prices","access":"unknown","period":null,"universe":null,"quote":"The dataset employed in this study comprises historical stock prices, specifically the open, close, high, and low values."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"HybridQNN2 achieves the lowest RMSE among quantum‑enhanced methods, confirming hybridization mitigates some quantum limitations.","kind":"performance","quote":"HybridQNN2 achieves the lowest RMSE among quantum-enhanced methods, confirming that hybridization mitigates some quantum limitations for this case."},{"finding":"Hybrid quantum‑classical models (HybridQNN1, HybridQNN2) consistently obtain lower RMSE than the pure CustomQNN model.","kind":"predictive-accuracy","quote":"HybridQNN models consistently achieve lower RMSE than CustomQNN, demonstrating the benefits of hybridization."},{"finding":"HybridQNN1 incurs the highest computational cost among the models, especially under k‑Fold cross‑validation.","kind":"performance","quote":"HybridQNN1 incurs the highest computational cost, particularly when using k-Fold cross-validation."},{"finding":"HybridQNN1 and HybridQNN2 show narrower error distributions with errors concentrated near zero, indicating higher stability than CustomQNN.","kind":"statistical","quote":"HybridQNN1 and HybridQNN2 demonstrate narrower distributions, suggesting that their errors are more concentrated around zero."},{"finding":"Increasing qubit count influences loss values, with different qubit configurations yielding varying loss magnitudes.","kind":"other","quote":"To assess the impact of qubit count on model performance, we analyze the loss values."}],"reported_performance":null,"out_of_sample":{"method":"cross-validation","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":62,"citations":{"cited_by_in_corpus":1,"by_independent_authors":1,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":1},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":1,"extracted_at":"2026-11-14T17:42:32Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}