Resolução de Problemas de Seleção de Características com Algoritmos Quânticos em Dados Financeiros Reais

Lucas Galvão; Otto Pires; Yan Alef Chagas; Maria Heloísa Fraga; Marcelo A. Moret

doi:10.14295/vetor.v34i2.18358

Authors

Lucas Galvão Latin American Quantum Computing Center, SENAI CIMATEC, Piatã, Salvador, Bahia
Otto Pires Centro Universitário SENAI CIMATEC, Salvador, Brasil
Yan Alef Chagas Centro Universitário SENAI CIMATEC, Salvador, Brasil
Maria Heloísa Fraga Centro Universitário SENAI CIMATEC, Salvador, Brasil
Marcelo A. Moret Centro Universitário SENAI CIMATEC, Salvador, Brasil https://orcid.org/0000-0003-0051-6309

DOI:

https://doi.org/10.14295/vetor.v34i2.18358

Keywords:

Feature selection, Financial Data, Quantum Annealing, QUBO, Machine Learning

Abstract

The financial sector faces significant challenges when dealing with high-dimensional datasets and a limited number of samples, making it difficult to build robust predictive models. Traditional machine learning techniques help mitigate these problems, but the presence of irrelevant and redundant features increases computational complexity. This article presents the application of quantum algorithms in feature selection using real data from the financial sector, demonstrating that these algorithms can improve the efficiency and accuracy of predictive models. The approach involves formulating the problem in terms of Unconstrained Quadratic Binary Optimization (QUBO), and its solution implemented in quantum annealer simulators. The experiments show promising results, which are analyzed using the Akaike Information Criterion metric. The results suggest that variational quantum algorithms have great application potential compared to traditional feature selection techniques.

Downloads

Download data is not yet available.

References

D. Liang, C.-F. Tsai, e H.-T. Wu, “The effect of feature selection on financial distress prediction,” Knowl. Based Syst., vol. 73, pp. 289–297, 2015.

J. Cai, J. Luo, S. Wang, e S. Yang, “Feature selection in machine learning: A new perspective,” Neurocomputing, vol. 300, pp. 70–79, 2018.

S. Velliangiri, S. Alagumuthukrishnan, e S. I. T. Joseph, “A review of dimensionality reduction techniques for efficient computation,” Procedia Computer Science, 2019. Disponível em: https://doi.org/10.1016/j.procs.2020.01.079

L. van der Maaten, E. O. Postma, e J. van den Herik, “Dimensionality reduction: A comparative review,” 2009. Disponível em: https://api.semanticscholar.org/CorpusID:12051918

C. Sorzano, J. Vargas, e A. Montano, “A survey of dimensionality reduction techniques,” 03 2014.

S. Ayesha, M. K. Hanif, e R. Talib, “Overview and comparative study of dimensionality reduction techniques for high dimensional data,” Information Fusion, vol. 59, pp. 44–58, 2020. Disponível em: https://doi.org/10.1016/j.inffus.2020.01.005

S. Khalid, T. Khalil, e S. Nasreen, “A survey of feature selection and feature extraction techniques in machine learning,” em 2014 Science and Information Conference, 2014, pp. 372–378.

C. Zoufal, R. V. Mishmash, N. Sharma, N. Kumar, A. Sheshadri, A. Deshmukh, N. Ibrahim, J. Gacon, e S. Woerner, “Variational quantum algorithm for unconstrained black box binary optimization: Application to feature selection,” Quantum, vol. 7, p. 909, 2023. Disponível em: https://doi.org/10.22331/q-2023-01-26-909

A. Abbas, A. Ambainis, B. Augustino, A. Bärtschi, H. Buhrman, C. Coffrin, G. Cortiana, V. Dunjko, D. J. Egger, B. G. Elmegreen et al., “Challenges and opportunities in quantum optimization,” Nature Reviews Physics, pp. 1–18, 2024. Disponível em: https://doi.org/10.1038/s42254-024-00770-9

S. Mücke, R. Heese, S. Müller, M. Wolter, e N. Piatkowski, “Feature selection on quantum computers,” Quantum Machine Intelligence, vol. 5, no. 1, feb 2023. Disponível em: https://doi.org/10.1007%2Fs42484-023-00099-z

G. Hellstern, V. Dehn, e M. Zaefferer, “Quantum computer based feature selection in machine learning,” IET Quantum Communication, vol. 5, no. 3, p. 232–252, 2024. Disponível em: https://doi.org/10.1049/qtc2.12086

R. Nembrini, M. Ferrari Dacrema, e P. Cremonesi, “Feature selection for recommender systems with quantum computing,” Entropy, vol. 23, no. 8, 2021. Disponível em: https://www.mdpi.com/1099-4300/23/8/970

K. Zhang, Y. Zheng, e Z. Li, “Dimension reduction for efficient data-enabled predictive control,” IEEE Control Systems Letters, vol. 7, pp. 3277–3282, 2022. Disponível em: https://doi.org/10.1109/LCSYS.2023.3322965

M. I. Jordan e T. Mitchell, “Machine learning: Trends, perspectives, and prospects,” Science, vol. 349, pp. 255 – 260, 2015. Disponível em: https://doi.org/10.1126/science.aaa8415

M. Rostami, K. Berahmand, E. Nasiri, e S. Forouzandeh, “Review of swarm intelligence-based feature selection methods,” Engineering Applications of Artificial Intelligence, vol. 100, p. 104210, 2021. Disponível em: https://www.sciencedirect.com/science/article/pii/S0952197621000579

J. Cai, J. Luo, S. Wang, e S. Yang, “Feature selection in machine learning: A new perspective,” Neurocomputing, vol. 300, pp. 70–79, 2018. Disponível em: https://www.sciencedirect.com/science/article/pii/S0925231218302911

A. J. Ferreira e M. A. T. Figueiredo, Boosting Algorithms: A Review of Methods, Theory, and Applications. New York, NY: Springer New York, 2012, pp. 35–85. Disponível em: https://doi.org/10.1007/978-1-4419-9326-7_2

F. Moroni, “A survey on feature selection methods for classification solved with quantum annealing,” Dissertação de mestrado, Politecnico di Milano, 2021. Disponível em: https://www.politesi.polimi.it/retrieve/04b2f778-f24a-46a2-9532-8aba12e74652/2021_12_Moroni.pdf

E. K. Grant e T. S. Humble, “Adiabatic quantum computing and quantum annealing,” em Oxford Research Encyclopedia of Physics, 2020.

L. Andrew, “Ising formulations of many NP problems,” Frontiers in physics, vol. 2, p. 5, 2014. Disponível em: https://doi.org/10.3389/fphy.2014.00005

E. F. Combarro, S. González-Castillo, e A. Di Meglio, A Practical Guide to Quantum Machine Learning and Quantum Optimization: Hands-on Approach to Modern Quantum Algorithms. Packt Publishing Ltd, 2023.

W. Van Dam, M. Mosca, e U. Vazirani, “How powerful is adiabatic quantum computation?” em Proceedings 42nd IEEE symposium on foundations of computer science. IEEE, 2001, pp. 279–287.

A. Cervera-Lierta, “Exact ising model simulation on a quantum computer,” Quantum, vol. 2, p. 114, 2018. Disponível em: https://doi.org/10.22331/q-2018-12-21-114

J. Xu, B. Tang, H. He, e H. Man, “Semisupervised feature selection based on relevance and redundancy criteria,” IEEE Transactions on Neural Networks and Learning Systems, vol. 28, pp. 1974–1984, 2017. Disponível em: https://doi.org/10.1109/TNNLS.2016.2562670

R. K. Nath, H. Thapliyal, e T. S. Humble, “Quantum annealing for automated feature selection in stress detection,” em 2021 IEEE Computer Society Annual Symposium on VLSI (ISVLSI). IEEE, 2021, pp. 453–457.

H. Akaike, “A new look at the statistical model identification,” IEEE Transactions on Automatic Control, vol. 19, no. 6, pp. 716–723, 1974. Disponível em: https://doi.org/10.1109/TAC.1974.1100705

S. Portet, “A primer on model selection using the Akaike information criterion,” Infectious Disease Modelling, vol. 5, pp. 111 – 128, 2020. Disponível em: https://doi.org/10.1016/j.idm.2019.12.010

A. Blumer, A. Ehrenfeucht, D. Haussler, e M. K. Warmuth, “Occam’s razor,” Information Processing Letters, vol. 24, no. 6, pp. 377–380, 1987. Disponível em: https://doi.org/10.1016/0020-0190(87)90114-1