Opening the 21st Century Technologies to Industries - On the Special Issue Machine Learning for Society

Aug 3, 2026

Machine learning techniques are presented as widely applicable artificial intelligence methods that address diverse societal needs through efficient solutions derived from historical data. The editorial introduces a Special Issue on “Machine Learning for Society” and summarizes contributions across multiple application domains. Coverage includes forecasting financial market crisis severity via neural networks with input factor selection, modeling and comparing exchange-rate prediction approaches with ARIMA and recurrent networks, and developing a big-data customer relationship management strategy for hospitality using multiple correspondence domain description.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages3

Reading Time8 min

AccessFree to download

Editorial

Opening the 21st Century Technologies to Industries

Stock Market Crisis Forecasting Using Neural Networks with Input Factor Selection

Recurrent Neural Networks and ARIMA Models for Euro/Dollar Exchange Rate Forecasting

A Big Data Approach to Customer Relationship Management Strategy in Hospitality

applied sciences Editorial Opening the 21st Century Technologies to Industries: On the Special Issue Machine Learning for Society Margarita Rodr½guez-Ib¡ñez 1, *, Cristina Soguero-Ruiz 2, Francisco-Javier Gimeno-Blanes 3 and Jos²-Luis Rojo-􀂁lvarez 2 Citation: Rodríguez-Ibáñez, M.; Soguero-Ruiz, C.; Gimeno-Blanes, F.-J.; Rojo-Álvarez, J.-L. Opening the 21st Century Technologies to Industries: On the Special Issue Machine Learning for Society. Appl. Sci. 2023, 13, 7371. [https://doi.org/](https://doi.org/)[ ](https://doi.org/)[10.3390/app13137371](10.3390/app13137371) Received: 8 June 2023 Accepted: 13 June 2023 Published: 21 June 2023 Copyright: © 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) . 1 Business Economics Department, Universidad Rey Juan Carlos, 28943 Fuenlabrada, Madrid, Spain 2 Signal Theory and Communication Department, Universidad Rey Juan Carlos, 28943 Fuenlabrada, Madrid, Spain; [cristina.soguero@urjc.es](cristina.soguero@urjc.es) (C.S.-R.); [joseluis.rojo@urjc.es](joseluis.rojo@urjc.es) (J.-L.R.-􀂁 .) 3 Communication Department, Miguel Hern¡ndez University, 03202 Elche, Alicante, Spain; [javier.gimeno@umh.es](javier.gimeno@umh.es) * Correspondence: margarita.rodriguez@urjc.es Keywords: machine learning; ARIMA; random series modelling; stock exchange; customer management; multiple correspondence analysis; domain description; hospitality; valuation Machine learning techniques, more commonly known today as artiﬁcial intelligence, are playing an increasingly important role in all aspects of our lives. Their applications extend to all areas of society where similar techniques can be accommodated to provide efﬁcient and interesting solutions to a wide range of problems. In this Special Issue entitled Machine Learning for Society [1], we present some examples of the applications of this typeof technique. From the valuation of unlisted companies to the characterization of clients, through the detection of ﬁnancial crises or the prediction of the behavior of the exchange rate, this group of works presented here has in common the search for efﬁcient solutions based on a set of historical data, and the application of artiﬁcial intelligence techniques. The techniques and datasets used, as well as the relevant ﬁndings developed in the different articles of this Special Issue, are summarized below. 1. Stock Market Crisis Forecasting Using Neural Networks with Input Factor Selection [2] The aim of this article [2] is to validate the use of neural networks to forecast the severity of ﬁnancial market crises by combining microeconomic, macroeconomic and ﬁnancial parameters. For this, a dataset of 30 variables was used, covering the period between January 1971 and May 2021 . A ﬁnancial crisis was deﬁned as a period of time between two peaks during which the S&P 500 index lost more than 20% of its value, and according to this criterion six periods of crisis were established. The development of a dimensional reduction technique based on variable inclusion iterative analysis, together with a forward forecast training model connected to a singlelayer neural network with three neurons, constitute the main contribution of this study. According to the ﬁndings of the article, the model selected through the suggested method performs better than the model used as a reference in terms of accuracy and stability. The chosen model achieved an accuracy rate of 91% compared to 83% for the previously published reference model. Additionally, since the chosen model requires a limited number of input variables, and therefore fewer parameters to estimate, the model thus deﬁned enjoys high robustness against overﬁtting. 2.

FAQs

What is the focus of the Special Issue introduced in the editorial?

It focuses on machine learning applications for society, highlighting efficient solutions built on historical data and AI techniques across different domains.

How does the issue present stock market crisis forecasting?

It describes validating neural networks to forecast the severity of financial market crises by combining microeconomic, macroeconomic, and financial parameters with dimensional reduction and forward forecasting.

Which models are compared for EUR/USD exchange-rate forecasting?

The issue summarizes a comparative study of ARIMA, Elman-type recurrent neural networks, and LSTM, evaluating short- and long-term accuracy using different window intervals.

Aug 3, 2026

Upload by Emma Wilson