{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T01:42:22Z","timestamp":1760060542221,"version":"build-2065373602"},"reference-count":50,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T00:00:00Z","timestamp":1757376000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"TUSUR Development Program for 2025\u20132036 of the Strategic Academic Leadership Program \u201cPriority 2030\u201d"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["BDCC"],"abstract":"<jats:p>This paper introduces novel inverse optimization algorithms (RC and DC) for neural network training in stock price forecasting in an attempt to overcome the traditional gradient descent limitation of local minima convergence. The key novelty is a stochastic algorithm for inverse problems adapted to neural network training, where target function values decrease iteratively through selective weight modification. Experimental analysis used closing price data from 40 Russian companies, comparing traditional activation functions (linear, sigmoid, tanh) with specialized functions (sincos, cloglogm, mish) across perceptrons and single-hidden-layer networks. Key findings show the superiority of the DC method for single-layer networks, while RC proves most effective for hidden-layer networks. The linear activation function with the RC algorithm delivered optimal results in most experiments, challenging conventional nonlinear activation preferences. The optimal architecture, namely, a single hidden layer with two neurons, achieved the best prediction accuracy in 70% of cases. The research confirms that inverse optimization algorithms can provide higher training efficiency than classical gradient methods, offering practical improvements for financial forecasting.<\/jats:p>","DOI":"10.3390\/bdcc9090235","type":"journal-article","created":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T19:16:17Z","timestamp":1757445377000},"page":"235","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Application of Inverse Optimization Algorithms in Neural Network Models for Short-Term Stock Price Forecasting"],"prefix":"10.3390","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6499-5893","authenticated-orcid":false,"given":"Ekaterina","family":"Gribanova","sequence":"first","affiliation":[{"name":"Image Processing and Artificial Intelligence Laboratory, Tomsk State University of Control Systems and Radioelectronics, Lenina Str., Tomsk 634050, Russia"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5934-7304","authenticated-orcid":false,"given":"Roman","family":"Gerasimov","sequence":"additional","affiliation":[{"name":"Image Processing and Artificial Intelligence Laboratory, Tomsk State University of Control Systems and Radioelectronics, Lenina Str., Tomsk 634050, Russia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3871-8993","authenticated-orcid":false,"given":"Elena","family":"Viktorenko","sequence":"additional","affiliation":[{"name":"Image Processing and Artificial Intelligence Laboratory, Tomsk State University of Control Systems and Radioelectronics, Lenina Str., Tomsk 634050, Russia"}]}],"member":"1968","published-online":{"date-parts":[[2025,9,9]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"6889","DOI":"10.1016\/j.eswa.2008.08.077","article-title":"A neural network with a case based dynamic window for stock trading prediction","volume":"36","author":"Chang","year":"2009","journal-title":"Expert Syst. Appl."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Rouf, N., Malik, M.B., Arif, T., Sharma, S., Singh, S., Aich, S., and Kim, H.-C. (2021). Stock Market Prediction Using Machine Learning Techniques: A Decade Survey on Methodologies, Recent Developments, and Future Directions. Electronics, 10.","DOI":"10.3390\/electronics10212717"},{"key":"ref_3","unstructured":"Bishop, C.M. (2006). Pattern Recognition and Machine Learning, Springer."},{"key":"ref_4","unstructured":"Box, G.E.P., and Jenkins, G.M. (1976). Time Series Analysis, Forecasting and Control, Holden Day."},{"key":"ref_5","first-page":"987","article-title":"Autoregressive conditional heteroscedasticity with estimates of the variance of united kingdom inflation","volume":"50","author":"Engle","year":"1982","journal-title":"Econom. J. Econom. Soc."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1016\/0304-4076(86)90063-1","article-title":"Generalized autoregressive conditional heteroskedasticity","volume":"31","author":"Bollerslev","year":"1986","journal-title":"J. Econom."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/07474938608800095","article-title":"Modelling the persistence of conditional variances","volume":"5","author":"Engle","year":"1986","journal-title":"Econom. Rev."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"347","DOI":"10.2307\/2938260","article-title":"Conditional heteroskedasticity in asset returns: A new approach","volume":"59","author":"Nelson","year":"1991","journal-title":"Econometrica"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1779","DOI":"10.1111\/j.1540-6261.1993.tb05128.x","article-title":"On the relation between the expected value and the volatility of the nominal excess return on stocks","volume":"48","author":"Glosten","year":"1993","journal-title":"J. Financ."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"931","DOI":"10.1016\/0165-1889(94)90039-6","article-title":"Threshold heteroskedastic models","volume":"18","author":"Zakoian","year":"1994","journal-title":"J. Econ. Dyn. Control"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Vukovic, D., Spitsyna, L.Y., Gribanova, E., Spitsin, V., and Lyzin, I. (2023). Predicting the Performance of Retail Market Firms: Regression and Machine Learning Methods. Mathematics, 11.","DOI":"10.3390\/math11081916"},{"key":"ref_12","first-page":"58","article-title":"A Survey on Data-Driven Techniques of Remaining Useful Life Assessment for Predictive Maintenance of the System","volume":"2","author":"Sarve","year":"2025","journal-title":"J. Sustain. Innov."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Lv, P., Wu, Q., Xu, J., and Shu, Y. (2022). Stock Index Prediction Based on Time Series Decomposition and Hybrid Model. Entropy, 24.","DOI":"10.3390\/e24020146"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Zhao, C., Hu, P., Liu, X., Lan, X., and Zhang, H. (2023). Stock Market Analysis Using Time Series Relational Models for Stock Price Prediction. Mathematics, 11.","DOI":"10.3390\/math11051130"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"102209","DOI":"10.1016\/j.frl.2021.102209","article-title":"Stock market prediction with deep learning: The case of China","volume":"46","author":"Liu","year":"2021","journal-title":"Financ. Res. Lett."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1007\/s00521-010-0407-3","article-title":"Comparison of new activation functions in neural network for forecasting financial time series","volume":"20","author":"Gomes","year":"2011","journal-title":"Neural Comput. Appl."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Akter, S., and Haider, M.R. (2025). mTanh: A Low-Cost Inkjet-Printed Vanishing Gradient Tolerant Activation Function. J. Low Power Electron. Appl., 15.","DOI":"10.3390\/jlpea15020027"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1016\/j.neucom.2022.06.111","article-title":"Activation functions in deep learning: A comprehensive survey and benchmark","volume":"503","author":"Dubey","year":"2022","journal-title":"Neurocomputing"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Misra, D. (2020, January 7\u201311). Mish: A Self Regularized Non-Monotonic Activation Function. Proceedings of the 31th British Machine Vision Conference, Manchester, UK.","DOI":"10.5244\/C.34.191"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"592","DOI":"10.28991\/ESJ-2024-08-02-014","article-title":"Comparison of Activation Functions in Convolutional Neural Network for Poisson Noisy Image Classification","volume":"8","author":"Khang","year":"2024","journal-title":"Emerg. Sci. J."},{"key":"ref_21","first-page":"1687","article-title":"Deep Network Approximation: Beyond ReLU to Diverse Activation Functions","volume":"25","author":"Zhang","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"3301","DOI":"10.11591\/eei.v13i5.7274","article-title":"A comparative analysis of activation functions in neural networks: Unveiling categories","volume":"13","author":"Bouraya","year":"2024","journal-title":"Bull. Electr. Eng. Inform."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1016\/j.neucom.2018.07.080","article-title":"A survey on metaheuristic optimization for random single-hidden layer feedforward neural network","volume":"335","author":"Han","year":"2019","journal-title":"Neurocomputing"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1016\/j.engappai.2017.01.013","article-title":"Metaheuristic design of feedforward neural networks: A review of two decades of research","volume":"60","author":"Ojha","year":"2017","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1767","DOI":"10.1007\/s10462-019-09719-2","article-title":"A survey of swarm and evolutionary computing approaches for deep learning","volume":"53","author":"Darwish","year":"2020","journal-title":"Artif. Intell. Rev."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"14482","DOI":"10.1109\/TNNLS.2023.3279381","article-title":"A Unified Analysis of AdaGrad With Weighted Aggregation and Momentum Acceleration","volume":"35","author":"Shen","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"345","DOI":"10.33330\/jurteksi.v9i3.2067","article-title":"Comparison of sgd, adadelta, adam optimization in gender classification using cnn","volume":"9","author":"Mandasari","year":"2023","journal-title":"JURTEKSI (J. Teknol. Dan Sist. Inf.)"},{"key":"ref_28","first-page":"8814","article-title":"Improving the efficiency of RMSProp optimizer by utilizing Nestrove in deep learning","volume":"13","author":"Elshamy","year":"2023","journal-title":"Dent. Sci. Rep."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"17095","DOI":"10.1007\/s00521-023-08568-z","article-title":"A modified Adam algorithm for deep neural network optimization","volume":"35","author":"Reyad","year":"2023","journal-title":"Neural Comput. Appl."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"E26397","DOI":"10.1016\/j.heliyon.2024.e26397","article-title":"Optimizing home energy management: Robust and efficient solutions powered by attention networks","volume":"10","author":"Nutakki","year":"2024","journal-title":"Heliyon"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1016\/j.neucom.2020.07.027","article-title":"Character-level neural network model based on Nadam optimization and its application in clinical concept extraction","volume":"414","author":"Lantian","year":"2020","journal-title":"Neurocomputing"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"22795","DOI":"10.1007\/s11042-020-10495-3","article-title":"Gradient based invasive weed optimization algorithm for the training of deep neural network","volume":"80","author":"Bai","year":"2021","journal-title":"Multimed. Tools Appl."},{"key":"ref_33","unstructured":"Liu, Z., Tilman, H., and Masahito, U. (2020, January 1\u201312). Neural Networks Fail to Learn Periodic Functions and How to Fix It. Proceedings of the 34th Conference on Neural Information Processing Systems, Vancouver, BC, Canada."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1007","DOI":"10.1007\/s40745-021-00354-9","article-title":"Genetic Algorithms in the Fields of Artificial Intelligence and Data Sciences","volume":"10","author":"Sohail","year":"2023","journal-title":"Ann. Data. Sci."},{"key":"ref_35","first-page":"101261","article-title":"A hyper-heuristic based reinforcement-learning algorithm to train feedforward neural networks","volume":"35","author":"Ozsoydan","year":"2022","journal-title":"Eng. Sci. Technol. Int. J."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"671","DOI":"10.1126\/science.220.4598.671","article-title":"Optimization by simulated annealing","volume":"220","author":"Kirkpatrick","year":"1983","journal-title":"Science"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"117588","DOI":"10.1016\/j.cma.2024.117588","article-title":"Integrating Differential Evolution into Gazelle Optimization for advanced global optimization and engineering applications","volume":"434","author":"Biswas","year":"2025","journal-title":"Comput. Methods Appl. Mech. Eng."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Huang, Y., Capretz, L.F., and Ho, D. (2021, January 5\u20137). Machine Learning for Stock Prediction Based on Fundamental Analysis. Proceedings of the IEEE Symposium Series on Computational Intelligence (SSCI), Orlando, FL, USA.","DOI":"10.1109\/SSCI50451.2021.9660134"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"651","DOI":"10.51594\/csitrj.v5i3.912","article-title":"Predicting stock market movements using neural networks: A review and application study","volume":"5","author":"Oyewole","year":"2024","journal-title":"Comput. Sci. IT Res. J."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Zaheer, S., Anjum, N., Hussain, S., Algarni, A.D., Iqbal, J., and Bourouis, S. (2023). A Multi Parameter Forecasting for Stock Time Series Data Using LSTM and Deep Learning Model. Mathematics, 11.","DOI":"10.3390\/math11030590"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1002\/for.3021","article-title":"Stock picking with machine learning","volume":"43","author":"Wolff","year":"2023","journal-title":"J. Forecast."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"4519","DOI":"10.1007\/s11063-022-11055-6","article-title":"Application of Meta-Heuristic Algorithms for Training Neural Networks and Deep Learning Architectures: A Comprehensive Review","volume":"55","author":"Kaveh","year":"2023","journal-title":"Neural Process. Lett."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"385","DOI":"10.1016\/j.wasman.2021.02.029","article-title":"Applying artificial neural networks (ANNs) to solve solid waste-related issues: A critical review","volume":"124","author":"Xu","year":"2021","journal-title":"Waste Manag."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1016\/j.ijpe.2016.10.021","article-title":"Single-hidden layer neural networks for forecasting intermittent demand","volume":"183","author":"Lollia","year":"2017","journal-title":"Int. J. Prod. Econ."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"112328","DOI":"10.1016\/j.asoc.2024.112328","article-title":"A dissolved oxygen levels prediction method based on single-hidden layer feedforward neural network using neighborhood information metric","volume":"167","author":"Luo","year":"2024","journal-title":"Appl. Soft Comput."},{"key":"ref_46","first-page":"27","article-title":"Development of iterative algorithms for solving the inverse problem using inverse calculations","volume":"4","author":"Gribanova","year":"2020","journal-title":"East.-Eur. J. Enterp. Technol."},{"key":"ref_47","first-page":"3","article-title":"Algorithm for Estimating the Time of Posting Messages on Vkontakte Online Social Network","volume":"12","author":"Gribanova","year":"2020","journal-title":"Int. J. Inf. Technol. Secur."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Gribanova, E. (2022). Elaboration of an Algorithm for Solving Hierarchical Inverse Problems in Applied Economics. Mathematics, 10.","DOI":"10.3390\/math10152779"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"104786","DOI":"10.1016\/j.frl.2023.104786","article-title":"Can ChatGPT assist in picking stocks?","volume":"59","author":"Pelster","year":"2023","journal-title":"Financ. Res. Lett."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"105433","DOI":"10.1016\/j.frl.2024.105433","article-title":"Can ChatGPT improve investment decisions? From a portfolio management perspective","volume":"64","author":"Ko","year":"2024","journal-title":"Financ. Res. Lett."}],"container-title":["Big Data and Cognitive Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-2289\/9\/9\/235\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:42:44Z","timestamp":1760035364000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-2289\/9\/9\/235"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,9]]},"references-count":50,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["bdcc9090235"],"URL":"https:\/\/doi.org\/10.3390\/bdcc9090235","relation":{},"ISSN":["2504-2289"],"issn-type":[{"type":"electronic","value":"2504-2289"}],"subject":[],"published":{"date-parts":[[2025,9,9]]}}}