Examinando por Autor "Sainz, Jorge"

Mostrando 1 - 10 de 10

A novel machine learning approach for evaluation of public policies: An application in relation to the performance of university researchers
(North Holland, 2019-12) Ballestar, Maria Teresa; Doncel, Luis MIguel; Ortigosa, Arturo; Sainz, Jorge
La investigación se ha convertido en el principal punto de referencia de la vida académica en las universidades modernas. Los incentivos a la investigación han sido un tema controvertido, debido a la dificultad de identificar quiénes son los principales beneficiarios y cuáles son los efectos a largo plazo. Aun así, se han adoptado nuevas políticas que incluyen incentivos financieros para aumentar la producción investigadora a todos los niveles posibles. Se ha dedicado poca literatura a la respuesta a esos incentivos. Para colmar esta laguna, realizamos nuestro análisis con datos de un programa de seis años desarrollado en Madrid (España). En lugar de utilizar un enfoque econométrico tradicional, diseñamos un modelo multinivel de aprendizaje automático para descubrir sobre quién, cuándo y durante cuánto tiempo tienen efecto esas políticas. El modelo empírico consiste en una agrupación longitudinal anidada automatizada (ANLC) realizada en dos etapas. En primer lugar, realiza una estratificación de los académicos y, en segundo lugar, realiza una segmentación longitudinal para cada grupo. La segunda parte considera la información sociodemográfica y académica de los investigadores y la evolución de su rendimiento a lo largo del tiempo en forma de variación porcentual anual de sus notas durante el periodo. La nueva metodología, cuya robustez se comprueba con una red neuronal artificial perceptrón multicapa con un algoritmo de aprendizaje de retropropagación, muestra que los investigadores titulares presentan una mejor respuesta a los incentivos que los titulares, y también que el género desempeña un papel importante en el mundo académico.
An artificial intelligence analysis of climate-change influencers' marketing on Twitter
(Wiley, 2022) Teresa Ballestar, María; Martín‐Llaguno, Marta; Sainz, Jorge
Designing marketing strategies with social media influencers are becoming increasingly relevant for setting political agendas. This study focuses on how two representative social influencers, Greta Thunberg and Bill Gates, engage in advising against climate change. The investigation uses 23,294 tweets posted by them or their followers citing them on climate change around the 25th edition of the United Nations Climate Change Conference. This study applies artificial intelligence and natural language processing to analyse the marketing mechanism of social influencers. We scrutinize the sentiment of the messages and then identify and analyse the different networks constructed around them to discern how pervasive a social influencer's message is. The results show that Thunberg and Gates follow different and unconnected strategies to deliver their messages to their followers.
Appendix to A Primer on Out-of-the-Box AI Marketing Mix Models
(2024-10-31) Estevez, Macarena; Ballestar, María Teresa; Sainz, Jorge
Customer segmentation in e-commerce: Applications to the cashback business model
(Elsevier, 2018-07-01) Ballestar, María Teresa; Grau-Carles, Pilar; Sainz, Jorge
This paper presents a segmentation of cashback website customers. The segmentation is based on customers' commercial activity and role within the site's social network. In this social network, customers profit from the transactions they make on affiliate websites. Mixing traditional marketing strategies with word-of-mouth recommendations is crucial for the success of this business model because these recommendations boost new customer acquisitions and strengthen the loyalty of existing customers. This study shows how the customer's role within the cashback website's social network determines the customer's behavior and commercial activity on the website. The segmentation presented describes the customer journey in terms of customer profitability and seniority. The findings explain customer behavior in e-commerce and the value of applying personalized retention strategies to each cluster rather than generic strategies or customer acquisition strategies. This paper describes how customers move between clusters, enabling practitioners to increase customer loyalty and long-term profitability.
Effectiveness of tutoring at school: A machine learning evaluation
(Elsevier, 2023) Ballestar, María Teresa; Cuerdo Mir, Miguel; Doncel Pedrera, Luis Miguel; Sainz, Jorge
Tutoring programs are effective in reducing school failures among at-risk students. However, there is still room for improvement in maximising the social returns they provide on investments. Many factors and components can affect student engagement in a program and academic success. This complexity presents a challenge for Public Administrations to use their budgets as efficiently as possible. Our research focuses on providing public administration with advanced decision-making tools. First, we analyse a database with information on 2066 students of the Programa para la Mejora de Éxito Educativo (Programme for the Improvement of Academic Success) of the Junta de Comunidades de Castilla y Léon in Spain, in 2018–2019, the academic year previous to the pandemic. This program is designed to help schools with students at risk of failure in Spanish, literature, mathematics, and English. We developed a machine learning model (ML) based on Kohonen self-organising maps (SOMs), which are a type of unsupervised (ANN), to group students based on their characteristics, the type of tutoring program in which they were enrolled, and their results in both the completion of the program and the 4th year of Compulsory Secondary Education (ESO). Second, we evaluated the results of tutoring programs and identified and explained how different factors and components affect student engagement and academic success. Our findings provide Public Administrations with better decision-making tools to evaluate and measure the results of tutoring programs in terms of social return on investment, improve the design of these programs, and choose the students to enrol.
Gender and generational cohort impact on entrepreneurs’ emotional intelligence and transformational leadership
(Springer, 2024) Esteves, José; Haro Rodríguez, Guillermo de; Ballestar, María Teresa; Sainz, Jorge
Emotional intelligence (EI) and leadership style are topics that have attracted a growing interest in the literature. In this study, we posit that entrepreneurs’ EI is an antecedent of transformational leadership (TL) while examining the moderating role of gender and generational cohort. Data were collected from 2,084 international entrepreneurs and analysed using multivariate analysis and hierarchical linear regression. The results confirm EI as an antecedent of TL and show that others’ emotion appraisal (OEA) and regulation of emotions (ROE) are the most contributing subdimensions of EI to TL. Moreover, the study also reveals significant gender and generational cohort differences for EI and TL. In one of the relevant findings, our research shows that only female Gen Z entrepreneurs have lower scores than their male counterparts. Although men’s EI scores are similar across generations, women’s scores are significantly higher in each older generation leaving ¡open questions for further research in the area.
Impact of robotics on manufacturing: A longitudinal machine learning perspective
(Elsevier, 2021-01-02) Ballestar, María Teresa; Díaz-Chao, Ángel; Torrent-i-Sellens, Joan; Sainz, Jorge
The evaluation of the impact of the adoption of industrial robotics on business is increasingly relevant in the current context of digital transformation. Although many companies are eager to adopt these technologies as a means to increase productivity, some concerns have been raised about the cost impact of the transformation, and its effect on the workforce. A growing body of literature is studying these phenomena but according to our review of it, there is no longitudinal perspective over 25 years illustrating the relationship between the attitude of companies to robotics and principal business indicators. This investigation uses an innovative machine learning model comprising an automated nested longitudinal clustering performed in two stages, and it is applied over a large sample of 4,578 companies from the Business Strategy Survey conducted by the Spanish Ministry of Finance and Public Administration. The findings of this research are novel in this field not only because of the longitudinal modelling applied in two stages but also because of the understanding of how companies’ characteristics and performance evolve over time depending on their degree of adoption of robotics. This knowledge is relevant for companies to understand the impact of their transformation to robotics. It also allows for the development of strategies that boost the efficiency of the companies, provides them with tools to protect them from negative financial events, and leads to an optimal sizing of their workforce.
Knowledge, robots and productivity in SMEs: Explaining the second digital wave
(Elsevier, 2020-01-02) Ballestar, María Teresa; Díaz-Chao, Ángel; Torrent-i-Sellens, Joan; Sainz, Jorge
This study provides new insights into the link among knowledge, industrial robotics and labor productivity by testing 12 hypotheses on samples of 1,515 and 1,380 Spanish manufacturing small and medium enterprises (SMEs) in 2008 and 2015. Our research has resulted in four main statements: Firsty, robotic devices are associated with better performance, higher productivity and employment rates, as well as with a more knowledge-intensive value process. Secondly, in 2015, robotics accounted for a 5% increase of SME productivity level (2% in 2008). Thirdly, between 2008 and 2015, SME labor productivity models have progressively granted greater relevance to multi-factor productivity components (knowledge flows and the use of robotics) and human capital. Finally, robot use has generated new complementarity relationships among the explanatory factors of labour productivity. In already-robotized SMEs, the knowledge spillover relates with more favorable effects of capital deepening and exports and to human capital in the non-robotized SMEs.
Predicting customer quality in e-commerce social networks: a machine learning approach
(Springer, 2019-12-14) Ballestar, Maria Teresa; Grau-Carles, Pilar; Sainz, Jorge
The digital transformation of companies is having a major impact on all business areas, especially marketing, where audiences are most volatile and loyalty is at its scarcest. Many large retail brands try to keep their client base interested by becoming partners in cashback websites. These websites are based on a specific type of affiliate marketing whereby customers access a wide range of merchants and obtain financial rewards based on their activities. Besides using this mix of traditional marketing strategies, cashback websites attract new target customers and increase existing customers’ loyalty through recommendations, using a word-of-mouth marketing strategy built on economic incentives for users who refer others to these sites. The literature shows that this strategy is one of the major areas of success of this business model because customers who join following recommendation are more active and are therefore more profitable and loyal to the brand. Nevertheless, the new users who are referred to these sites vary considerably in terms of the number of transactions they make on the site. This study advances research on the design of recommendation-based digital marketing strategies by providing companies with a predictive model. This model uses data science, including machine learning methods and big data, to personalize financial incentives for users based on the quality of the new customers they refer to the cashback website. Companies can thus optimize and maximize the return on their marketing investment.
Why is your company not robotic? The technology and human capital needed by firms to become robotic
(Elsevier, 2022) Ballestar, María Teresa; García-Lazaro, Aida; Sainz, Jorge; Sanz, Ismael
The impact of companies’ adoption of robotics is increasingly interesting. This study aims to elucidate how the adoption of these technologies will affect companies and society. Companies that use these technologies expect to gain a competitive advantage, but robotization implies risks that must be managed by companies and governments. This research focuses on one of the most sensitive elements of this transformation process—the workforce. First, we analyze the characteristics of the workforce and the degree of adoption of robotics using a sample of 4,640 firms with 26 years of observation. We develop a predictive model using a supervised artificial neural network multilayer perceptron (ANN-MLP) to evaluate a company’s readiness to make this transformation according to its workforce’s characteristics. Second, we focus on the characterization and segmentation of the companies for which the ANN-MLP is unable to correctly predict the degree of adoption of robotics. This classification failure means that there are unidentified factors that determine why a company has a workforce composition and structure that do not correspond to its expected degree of robotization. For this analysis, we investigate the main business indicators of these companies and cluster them using an unsupervised artificial neural network, specifically the Kohonen self-organizing map. Our findings will enable companies to understand the importance of transforming to robotics at the right moment, considering factors such as the optimum structure and composition of the workforce. The combination of technology and human capital is the key to boosting the efficiency of the transformation process toward robotics. At this point, a recommendation model to determine whether the company has sufficient maturity to make the transition is crucial for decision makers.