{"paper_id":"2412.10860","title":"Classification of Financial Data Using Quantum Support Vector Machine","authors":["Seemanta Bhattacharjee","MD. Muhtasim Fuad","A. K. M. Fakhrul Hossain"],"paper_date":"2024-12-14","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2412.10860v1","page_url":"https://thequant.space/flowcharts/classification-of-financial-data-using-quantum-support-vecto/","scores":{"empirical_rigor":4,"math_complexity":7.5,"quadrant":"Lab Rats"},"proposes":{"status":"available","statement":"The paper proposes a quantum kernel based on the Pauli Y YY feature map as the best performing model for the DSEx Broad Index dataset and verifies the Phase Space Terrain Ruggedness Index metric.","quote":"we report empirical quantum advantage in our work, using several quantum kernels and proposing the best one for this dataset while verifying the Phase Space Terrain Ruggedness Index metric.","summary":"Quantum Support Vector Machine is a kernel-based approach to classification problems. We study the applicability of quantum kernels to financial data, specifically our self-curated Dhaka Stock Exchange (DSEx) Broad Index dataset. To the best of our knowledge, this is the very first systematic…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The problem is treated as a binary classification task.","type":"data","stated":"implied","quote":"This study focuses on a binary classification problem using the Dhaka Stock Exchange Broad Index dataset."},{"assumption":"The curated DSEx dataset is representative of stock market behavior.","type":"market","stated":"implied","quote":"stock market data exhibit non-stationary behavior, with the statistical properties of the data changing over time, making this problem a prime candidate for quantum algorithms."},{"assumption":"Quantum feature maps can be implemented on near‑term quantum devices with short‑depth circuits.","type":"model","stated":"explicit","quote":"This is from a family of feature maps conjectured to be hard to simulate classically"},{"assumption":"Balanced Accuracy and F1 Score are sufficient metrics to evaluate classification performance.","type":"statistical","stated":"explicit","quote":"Balanced Accuracy and F1 Score are used to measure the kernels’ performance for this research."}]},"datasets":{"status":"available","items":[{"name":"DSEx Broad Index dataset","provider":"Investing.com and usagold.com","kind":"market-prices","access":"public","period":null,"universe":"Top 20% listed firms by market cap and liquidity on Dhaka Stock Exchange","quote":"The curated dataset was created by merging the two datasets, resulting in a total of 460 data points."}],"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":"The Pauli Y YY quantum kernel consistently outperformed all other quantum kernels and classical SVM models across every configuration tested.","kind":"performance","quote":"the kernels generated using the kernels built using the Pauli Y YY feature map consistently outperformed all other quantum kernels and classical Support Vector Machine (SVM) models for every point in the feature-dataset configuration space."},{"finding":"Quantum kernels achieved higher Balanced Accuracy than classical SVMs on datasets where classical performance was near its minimum.","kind":"predictive-accuracy","quote":"Figure 3 implies the impact and importance of the quantum approach in real‑world scenarios where we face the scarcity of stock market data and where the classical SVM performs worse than the average performance."},{"finding":"Empirical Quantum Advantage (EQA) was observed for all problem instances in the configuration space.","kind":"theoretical","quote":"While comparing the position of the data points with the horizontal ’zero‑advantage line’ in Figure 3, we observe EQA for all problem instances in the configuration space."},{"finding":"The study demonstrates the practical applicability of quantum machine learning for financial data and suggests potential for future quantum advantage.","kind":"other","quote":"In this work, we demonstrate the practical applicability of quantum machine learning for financial data."}],"reported_performance":null,"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":30,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"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":"2026-11-14T17:49:56Z"},"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/"}