doi: 10.56294/dm2024.599

ORIGINAL

Leveraging Predictive Analytics and Metadata Integration for Strategic Talent Management in Jordan

Aprovechamiento del análisis predictivo y la integración de metadatos para la gestión estratégica del talento en Jordania

Anber Abraheem Shlash Mohammad¹ *, Suleiman Ibrahim Mohammad^2,3 *, Badrea Al Oraini⁴ *, Ayman Hindieh⁵ *, Asokan Vasudevan⁶ *, Mohammad Faleh Ahmmad Hunitie⁷ *, Hongli Long⁸ *, Imad Ali⁹ *

¹Digital Marketing Department, Faculty of Administrative and Financial Sciences, Petra University. Jordan.

²Electronic Marketing and Social Media, Economic and Administrative Sciences Zarqa University. Jordan.

³Research follower, INTI International University. 71800 Negeri Sembilan, Malaysia.

⁴Business Administration Department. Collage of Business and Economics, Qassim University.

Qassim, Saudi Arabia

⁵Electronic Marketing and Social Media, Economic and Administrative Sciences Zarqa University. Jordan.

⁶Faculty of Business and Communications, INTI International University. 71800 Negeri Sembilan, Malaysia.

⁷Department of Public Administration, School of Business, University of Jordan. Jordan

⁸Faculty of Liberal Arts, Shinawatra University. Thailand

⁹GNIOT Institute of Management Studies, Greater Noida, Uttar Pradesh, India.

How to Cite: Shlash Mohammad AA, Ibrahim Mohammad S, Al Oraini B, Hindieh A, Vasudevan A, Ahmmad Hunitie MF, et al. Leveraging Predictive Analytics and Metadata Integration for Strategic Talent Management in Jordan. Data and Metadata. 2025;3:.599. https://doi.org/10.56294/dm2024.599

Submitted: 21-05-2024          Revised: 10-09-2024          Accepted: 17-12-2024          Published: 18-12-2024

Editor: Adrián Alejandro Vitón Castillo

Corresponding author: Suleiman Ibrahim Mohammad *

ABSTRACT

Introduction: talent management is critical for organizational performance. This research explored the use of predictive analytics on employee metadata, including profile analysis, performance history, training records, and career progression scores, to optimize retention and promotion strategies in Jordanian organizations. The study provided insights into the effectiveness of integrating predictive tools with metadata to enhance talent management outcomes.

Method: a quantitative research design, incorporating descriptive and correlational approaches, was employed. Data were collected from 257 HR professionals and decision-makers using structured questionnaires and organizational records. Statistical techniques such as linear and logistic regression, correlation analysis, and machine learning models were used to examine the predictive influence of variables like age, training hours, performance ratings, and career progression scores.

Results: the results indicated that training hours, performance ratings, and career progression scores are good predictors of retention rates while age and tenure were strong predictors of success promotion. Machine learning models strongly predicted retention outcomes with an attainment of an R-squared score of 0,671, so predictive analytics can enhance efficiency in decision-making. Moderate use of Predictive analytic tools was related to improved promotion outcomes suggests a balance between data-driven and human judgment approaches.

Conclusion: the study contributed to the growing discourse on data-driven HR practices, contextualizing findings within Jordanian organizations. It highlighted the ethical and cultural considerations necessary for implementing metadata-driven tools. The results underscored the potential of predictive analytics to improve talent management processes, ultimately supporting the achievement of strategic HR goals.

Keywords: Talent Management; Metadata; Predictive Analytics; Human Resource Management; Machine Learning.

RESUMEN

Introducción: la gestión del talento es fundamental para el rendimiento de las organizaciones. Esta investigación exploró el uso de análisis predictivos en metadatos de empleados, incluyendo análisis de perfiles, historial de rendimiento, registros de formación y puntuaciones de progresión profesional, para optimizar las estrategias de retención y promoción en organizaciones jordanas. El estudio proporcionó información sobre la eficacia de integrar herramientas predictivas con metadatos para mejorar los resultados de la gestión del talento.

Método: se empleó un diseño de investigación cuantitativo que incorporaba enfoques descriptivos y correlacionales. Se recopilaron datos de 257 profesionales de RRHH y responsables de la toma de decisiones mediante cuestionarios estructurados y registros organizativos. Se utilizaron técnicas estadísticas como la regresión lineal y logística, el análisis de correlación y los modelos de aprendizaje automático para examinar la influencia predictiva de variables como la edad, las horas de formación, las calificaciones de rendimiento y las puntuaciones de progresión profesional.

Resultados: los resultados indicaron que las horas de formación, las puntuaciones de rendimiento y las puntuaciones de progresión profesional son buenos predictores de las tasas de retención, mientras que la edad y la permanencia en el puesto fueron fuertes predictores del éxito en la promoción. Los modelos de aprendizaje automático predijeron en gran medida los resultados de retención con una puntuación R-cuadrado de 0,671, por lo que el análisis predictivo puede mejorar la eficiencia en la toma de decisiones. El uso moderado de herramientas de análisis predictivo se relacionó con mejores resultados de promoción, lo que sugiere un equilibrio entre los enfoques basados en datos y en el juicio humano.

Conclusión: el estudio contribuyó al creciente discurso sobre las prácticas de RRHH basadas en datos, contextualizando los resultados dentro de las organizaciones jordanas. Puso de relieve las consideraciones éticas y culturales necesarias para implantar herramientas basadas en metadatos. Los resultados subrayaron el potencial del análisis predictivo para mejorar los procesos de gestión del talento, apoyando en última instancia la consecución de los objetivos estratégicos de RRHH.

Palabras clave: Gestión del Talento; Metadatos; Análisis Predictivo; Gestión de Recursos Humanos; Aprendizaje Automático.

INTRODUCTION

The integration of predictive analytics into talent management is a sea change in the way organizations conceptualize human resource strategies, providing robust mechanisms to enhance decision-making processes. Predictive analytics applies complex statistical and machine learning techniques to analyze patterns and forecast outcomes, thus helping HR professionals tackle issues such as employee retention, promotion, and engagement with data-driven precision.^(1,2) Apart from that, the use of metadata-comprehensive datasets containing complete employee profiles, performance histories, and career progression records-offers a holistic approach to optimizing talent management strategies. In Jordan, adoption of such technologies is increasingly crucial for organizations struggling to retain skilled talent and foster a competitive workforce amidst an evolving economic landscape.^(3,4,5)

Talent management has conventionally been considered one of the significant building blocks for organizational success, in which retention and promotion are identified as crucial for long-term performance and sustainability.^(6,7) Several studies have established that effective talent management strategies reduce turnover, improve productivity, and engender employee loyalty.^(8,9) These challenges are further compounded in Jordan by a workforce characterized by diverse demographic and cultural dynamics. Predictive analytics integrated into metadata on HR practices hold the promise of surmounting these challenges through organizational systematic analysis of employee attributes that identify the key predictors of retention and promotion outcomes.^(10,11,12)

Predictive analytics in talent management marks a sea change in how organizations approach human resource strategies by providing robust mechanisms for enhancing decision-making. Predictive analytics uses advanced statistical and machine learning techniques to identify patterns and forecast outcomes that allow HR professionals to address employee retention, promotion, and engagement with data-driven precision.⁽¹³⁾ This approach, along with the use of metadata, or comprehensive datasets of employee profiles, performance histories, and career progression records, gives an approach toward optimization of talent management strategies from every angle. In Jordan, this is becoming increasingly crucial as organizations tackle retention issues with skilled talent and building up a competitive workforce amid a shifting economic landscape.^(14,15,16)

Talent management is well considered the core underpinning of organizational success. Talent retention and promotion have always been vital to the process that ensures long-term performance and sustainability.⁽¹⁷⁾ Research has consistently stated that effective talent management strategies reduce turnover and enhance productivity and employee loyalty. Specific challenges in Jordan are magnified by a diversified demographic and cultural dynamism in the workforce.^(3,18) Integrating predictive analytics with metadata will have the potentials to solve these challenges when organizations are going systematically through employee attributes in order to identify major predictors of retention and promotion outcome.

It’s not only an operational advantage to be able to predict employee behaviors and outcomes but a strategic one in a highly competitive and globalized business environment. The research evidence suggests that organizations investing in predictive analytics for HR decision-making enjoy significant gains in efficiency and accuracy, reducing the time and biases associated with traditional methods.^(13,19) For example, features such as hours of training, performance appraisals, and career development scores have been studied with the help of machine learning models to make effective retention predictions with remarkable accuracy.⁽²⁰⁾ This is also in support of global research findings on the increasing need to adopt data-driven approaches to enhance HR decision-making.

Despite the potential, predictive analytics uses in human resource practices do have their challenges. Some critics are of the view that such over-reliance on an algorithm might unintentionally import biases or fail on some critical contextual factors like cultural nuances and organizational values.^(21,22) This underlines the fact that a balanced approach is necessary, which integrates predictive tools with human judgment, considering contexts like Jordan, where cultural and economic factors have a strong bearing on workforce dynamics. Research on Middle Eastern organizations supports the view that aligning data-driven practices with local cultural norms is critical to ensuring employee satisfaction and organizational effectiveness.^(23,24)

The problem statement the research aims to investigate is to find an approach toward talent management in Jordan in such a way that both predictive analytics and metadata will be incorporated for maximum outcomes. Despite the growing literature concerning data-driven strategies for HR, the nature of adapting such approaches remains unclear for Jordan. The present research paper attempts to fill this lacuna by studying the relationships of various metadata attributes of employees, such as performance history, training record, and demographic profile, with HR outcomes like retention or promotion. This, in turn, it hopes will deliver actionable insight into how organizations will be able to move their talent management practices in close coordination with cultural and ethical considerations.

This research is important because it will contribute to the discussion of data-driven HR management, which is still in its infancy in many parts of the world. The value of this study thus lies in the fact that it might contribute to a greater good, creating sustainable and competitive organizations by showing how predictive analytics can enhance decision-making efficiency, reduce biases, and foster a more equitable workplace. It also stresses the importance of combining global best practices with local insight in order to ensure that predictive tools are both effective and culturally sensitive.

The underlying research statement for this study would be that the integration of predictive analytics with metadata considerably enhances talent management in Jordan, yielding better retention and promotion outcomes, while concurrently allowing for a non-discriminatory and effective process of decision-making. That is derived from the fact that recent literature has recognized data-driven approaches as the cornerstone for modern HR management in line with theoretical frameworks emphasizing the strategic importance of human capital development. It confirms that this hypothesis will be investigated through statistical and machine learning analysis. While so doing, the study presents a road map on how such organizations can adopt predictive tools in effective and ethical manners.

The objective of the study is to evaluate the role of metadata attributes and predictive analytics tools in enhancing talent management outcomes by identifying key correlations, improving decision-making efficiency, reducing biases, and promoting data-driven HR strategies within the context of Jordanian organizations.

Literature review

Metadata Analytics

The core of the HR analytics includes metadata, such as age, sex, role, performance records, training, and career movements. Pandey and Mehta have demonstrated how employee profiles impact organizational retention and career development by applying customized metadata analysis to improve employees work engagement.⁽²⁵⁾ Also, Darwish et al. discuss that training and tenure significantly predict promotion and retention using data.⁽²⁶⁾ In this regard, Alabbas et al. emphasized that in Jordan, demographic and cultural metadata have made talent management take shapes that are unique.⁽²⁷⁾

Predictive analytics tools apply algorithms and machine learning to metadata to forecast HR outcomes. Likhitkar and Verma proved that these tools improve decision-making by identifying unbiased routes for promotion.⁽²⁸⁾ Levenson also showed how analytics eliminate waste and make talent management interventions more precise.⁽²⁹⁾ However, according to Anderson et al. algorithms have their biases and need to be balanced with human judgment.⁽³⁰⁾

Talent management outcome

The retention and success of promotions, and the impacts of training programs, serve as direct measures for the effectiveness of talent management. According to Eisenberger and Stinglhamber perceived organizational support, such as professional development, influences retention and thus can be a predictor of employee loyalty over time.⁽³¹⁾ Aguwamba et al. established that clear career progression frameworks relate to better job satisfaction and reduced turnover.⁽³²⁾ Levenson has identified the way analytics-based approaches help elevation processes become better aligned with the goals of an organization.⁽²⁹⁾

Predictive analytics enhances the efficiency of decision-making by streamlining HR processes. Davenport and Harris found that data-driven tools reduced the time taken for workforce evaluation up to 30 % to meet HR decisions with organizational strategy.⁽³³⁾ Binns underlined that human judgment interacts with algorithmic insight in making balanced decisions.⁽³⁴⁾ Al‐Husan et al. observed that HR analytics tailored to context increased process efficiency in Middle Eastern contexts without violating cultural boundaries.⁽³⁵⁾

In HR analytics, the reduction of bias has remained a focus. Bohnet et al. presented that structured data analysis mitigates subjective biases in hiring and promotion.⁽³⁶⁾ Kumar et al. stressed the need for algorithmic models to be transparent for them to be fair and non-discriminatory.⁽³⁷⁾ Al‐Husan et al. added that as analytics get aligned with the cultural expectations, perceived inequities in the management of the workforce will be minimized.⁽³⁵⁾

Organizational Context and Cultural Factors

Organizational context is highly influential in the effectiveness of metadata and predictive tools, for instance, the type of industry, its size, and how well HR technologies have been adopted. Barney and Wright said that a firm with a developed technological framework attains competitive advantage because it can leverage and optimize its HR functions in the best possible way.⁽³⁸⁾ According to Nurimansjah technology readiness enables adaptation to modern contextual demands on the workforce in regards to HR practices.⁽³⁹⁾ Al-Dmour et al. also proved that not all industries are on an equal footing regarding digitalization of HR functions in Jordan and hence are less effective.⁽⁴⁰⁾

In collectivist societies, such as Jordan, cultural factors even more strongly moderate the effectiveness of HR analytics. Ameer and Khan claimed that culturally sensitive analytics frameworks raise the level of employee engagement.⁽⁴¹⁾ Eisenberger et al. reiterated that perceived organizational support is essential in order to make analytics-driven practices congruent with expectations set by employees.⁽⁴²⁾ Shin et al. supported the incorporation of cultural knowledge into algorithmic models to better their relevance and acceptance.⁽⁴³⁾

Population Economics

Demographic variables like age, gender, and education also have a significant impact on the strategy of talent management. According to Poisat et al. employees with more age and length have more organizational loyalty.⁽⁴⁴⁾ Kroese explained that there is a difference in gender which affects the opportunities of training, and to ensure equity, the analyses should be controlled.⁽⁴⁵⁾ Wöcke and Heymann, the education level also decides the rates of promotion and retention, so demographic variables are very crucial for consideration in HR analytics.⁽⁴⁶⁾

Market conditions and employment trends are the economic factors that affect the talent management outcomes. According to Patro, the economic situation is important in determining the flow of employees, which directly impacts the retention policies for employees.⁽⁴⁷⁾ Canedo et al. has given an elaboration of how changes in the global economy serve as a catalyst in the adoption of HR technology.⁽⁴⁸⁾ Rawabdeh and Nawafleh indicated that regional economic problems within Jordan impact employment processes and therefore analyses need to be done with consideration to specific contexts.⁽⁴⁹⁾

Research Gap

The literature on this is mostly from global or Western contexts, while less is known about the cultural factors in countries like Jordan that moderate the performance of predictive analytics. Studies by Rawabdeh and Nawafleh indicate that culturally insensitive approaches may reduce the perceived fairness of analytics-driven decisions.⁽⁴⁹⁾ Gurusinghe et al. and Simbeck indicate that these models may be discriminatory, but far less concern is shown in theoretical frameworks for embedding such predictive applications ethically within HR policy.^(50,51)

There are ethical implications related to the protection of employees’ data privacy, which should be transparently as fair all these demand more detailed study, mainly in countries that have not reached similar thresholds in applying such regulatory standards. Much research done in the past is focused on immediate benefits derived from the application of this predictive analytics by Levenson and Sharmila et al., among others.^(29,52) However, long-term organizational effects of such tools on employee trust, satisfaction, and performance are limited. Except for a few, like Mahendran and Krithika, that dealt with specific industries’ HR analytics adoption, cross-industry analysis is hard to find. Identifying how predictive tools are working out in various sectors within Jordan can give stronger generalizations.⁽⁵³⁾

This requires region-specific studies, ethical frameworks, and longitudinal approaches to ensure that predictive analytics in talent management are both effective and equitable.

Hypotheses and Conceptual Model Development

On the basis of the reviewed literature, below mentioned hypothesis were developed and a conceptual model of the study was framed (figure 1).

1 H1: Metadata attributes such as employee profiles and performance histories significantly influence the effectiveness of talent management outcome.

2 H2: Predictive analytics tools positively impact the accuracy of talent management outcome.

3 H3: Strong correlations exist between metadata analytics and successful talent management outcomes.

4 H4: Integrating metadata into predictive analytics models enhances decision-making efficiency and reduces biases in talent management outcomes.

5 H5: The application of predictive analytics and metadata integration in the Jordanian context is positively associated with improved organizational talent management performance.

Figure 1. Conceptual Model of the study

METHOD

Research Design

This study adopts a quantitative research design to establish the level to which predictive analytics, enriched with metadata, may optimize talent management strategies within Jordan. This study is a descriptive and correlational research method of establishing the relationships existing between the metadata of employees and the decision-making processes of the organizations. Using predictive analytics and regression models, the research tried to create actionable insights into how metadata can serve the dual purpose of improving outcomes in human resources, such as talent retention and promotion potential.

Population and Sample

The targeted organizations in the research are across different sectors in Jordan, including public and private enterprises, the focus was on industries like finance, technology, manufacturing, and education. A full population included HR professionals, talent managers, and analytics specialists involved in making talent management decisions. Thereafter, a stratified random sampling method was carried out in such a manner that representatives of small-sized and large-sized organizations were assured, together with varying states of the adoption of Human Resources’ technologies. The total population yielded a sample size of 257 participants. The participants in these interviews are a mix of decision-makers and analytics practitioners who either have access or insider knowledge with regard to the organizational metadata and the interest in and applications of talent management thereof.

Measures

The research adopted both primary and secondary data in order to ensure comprehensive insights. Primary data were obtained through structured surveys and interviews of HR professionals on their perceptions of predictive analytics and metadata integration. Items of the survey included ease of use, perceived accuracy, and impact on decision-making using a 5-point Likert scale. The secondary data were obtained from organizational HR systems, providing anonymized employee metadata regarding performance reviews, training records, career progressions, and demographic profiles, among other areas. This rich dataset allowed a rather more intensive investigation of how metadata features impinge on the outcomes in predictive analytics for talent management.

Analytical Methods

Different statistical and analytical methods have been carried out with the data analysis. It had been summarized using descriptive statistics in presenting data in order to obtain an overview of all central tendencies and variabilities in different variables. Regression models have been developed that outline the associations of results of Predictive Analytics and metadata attributes related to the history of training, scores of performances, and the acquisition of skills. Besides this, with correlation analysis, one would obtain assessments regarding strengths and directions of relationships between associations. Machine learning algorithms were run to predict attributes like employee turnover and chances of being promoted, providing enhanced prediction accuracy based on the metadata attributes. To present such findings in an easy-to-consume manner, data visualizations by Tableau and Python libraries displayed comprehensive yet clear visualizations, given the complexity of emergent patterns.

Ethical Considerations

Ethical considerations formed a cornerstone for the research in order to ensure that all processes were in conformity with the highest degree of integrity and compliance standards. All participants were fully informed of the purpose of the study and provided informed consent before making their contributions. Individual identifications were anonymized from the employee metadata in adherence to data protection laws in Jordan. The participation was fully voluntary, and the right to withdraw from the study at any moment in time, without further consequences, was also a right afforded to all participants. All data were securely stored on encrypted servers accessible only to authorized research team members. This ensured confidentiality and reliability in the research findings while maintaining trust with all participants.

RESULTS

Descriptive analyses (table 1) provided important insights into demographic and developmental attributes of the studied workforce: The average age was 38,0 years (SD = 8,5) median, 38 years, reflected that the population was well represented in the mid-career bracket. The hours of training, considered a very important indicator of employees’ development, averaged 35,8 hours-standard deviation of 10,3-skewed to the right, indicating that on the whole, the sample under survey has very strongly invested in enhancing their skills. Employee retention stands very high at an average of 82 % with a standard deviation of 5 %. These show that the organization is focused on enabling employee growth and stability. The rather low dispersion of the retention rate series would indicate a consistent effort in talent management practices.

Table 1. Descriptive Analysis
Variable	Mean	Median	Standard Deviation	Minimum	Maximum
Age	38	38	8,5	25	55
Training Hours	35,8	35	10,3	10	50
Retention Rate	0,82		0,05	0,7	0,9

A linear regression model was fitted to examine the association of the retention rate with the four most important predictors: Age, Performance Rating, Training Hours, and Career Progression Score. The analysis showed that the model fit is strong, an adjusted R-square value of 0,461 means that the mentioned predictors account for 46,1 % of the variability in the retention rate. Meanwhile, all four selected predictors are of significant contributions.

Based on the study’s linear regression analysis, the equation 1 for predicting Retention Rate is:

Age was positively associated with retention rates, with a regression coefficient of about 0,00245, though at a p-value of less than 0,001, which was comparatively smaller in effect size. On the other hand, performance rating had a strong positive influence: B = 0,02510, p < 0,001, hence indicating that higher-rated performers were more likely to continue with the organization. Among these, Training Hours emerged as a significant predictor: B = 0,00380, p < 0,001, pointing out the importance of continuous professional development in talent retention. Similarly, Career Progression Score showed a positive association with retention: B = 0,01890, p < 0,001, reflecting that opportunities for advancement within the organization are fundamental in fostering loyalty. These findings together emphasize the fact that an all-inclusive employee development and evaluation system is very crucial for bringing positive change in retention outcomes.

For your logistic regression model predicting Promotion Success, the equation 2 is:

To obtain the probability of promotion success (ppp) from the logistic regression model:

where:

Logistic regression analysis was used to examine the likelihood of promotion success with Age, Tenure, Training Hours, and levels of Predictive Analytics Usage as predictors. The model fit well, residual deviance equalled 258,25, and AIC was 270,25. Of the predictors, Age proved to be a significant positive factor (B = 0,03501, p < 0,001), which reflects that older employees were more likely to achieve promotions, probably reflecting their accumulated experience.

Tenure also shows a significant influence on the success of promotion, wherein the coefficient is B = 0,05250, and p = 0,007, again highlighting the importance of long-term commitment to an organization. Similarly, Training Hours were found to be significant, with the coefficient being B = 0,01580 and the p-value 0,008, indicating that efforts of skill enhancement do pay in terms of upward mobility within the organizational setup. Furthermore, medium Predictive Analytics Usage levels were found to relate significantly to the promotion outcome: B = 0,71052, p = 0,001B = 0,71052, p = 0,001B=0,71052,p=0,001. This evidences that moderate application of predictive tools effectively supports talent evaluation processes. These findings put additional emphasis on the multi-dimensional nature of promotion determinants, where individual attributes and organizational analytics are standing at the forefront.

The correlation analysis (figure 2) further explained how the study variables intercorrelated. Retention rate was moderately positively related to the number of training hours received, as well as to career progression grade, with r= 0,52 and 0,57, respectively, indicating that employees get more training and perceive clear career advancement possibilities. Age also showed a weaker but positive linkage with retention rate, r = 0,40, insinuating that older employees would have greater organizational attachment.

Figure 2. Correlation Analysis

Training Hours also associated significantly with other variables related to Performance Rating: r=0,35 and Career Progression Score: r=0,38, further establishing these tenets that employee development correlates to individual and organizational survival. These correlations indicate certain connectedness of metadata attributes that drive talent management outcomes.

A machine learning model (figure 3) was developed for the prediction of retention rate, including Age, Performance Rating, Training Hours, and Career Progression Score, among other predictors. This model has put up an excellent performance, as can be confirmed by its R-squared value of 0,671, hence explaining 67,1 % of the variance in retention rates. The RMSE was 0,0682, and MAE was 0,0521, which indicated the very high accuracy with very low error of the predictions.

Figure 3. Machine Learning Results

The predicted retention rates were rather close to the actual value (figure 4), demonstrating the reliability and robustness of the model while making decisions using metadata. This speaks once more to the usefulness of machine learning approaches in digging up complex patterns and making useful inferences about dynamics in play in employee retention.

Figure 4. Actual vs Predicted Retention Rates

Hypothesis Testing

Hypothesis 1 was confirmed by the linear regression analysis, since Performance Rating (B = 0,02510, p < 0,001), Training Hours (B = 0,00380, p < 0,001), and Career Progression Score (B = 0,01890, p < 0,001) were found to be significant predictors of retention rates. The findings indicate that metadata attributes related to employee development and evaluation hold the key in relation to the nature of the retention outcome.

Logistic regression again showed that Tenure had a significant effect on whether the promotion was successful or not, B = 0,05250, p = 0,007, and Training Hours, B = 0,01580, p = 0,008, hence reinforcing the importance of metadata attributes in making talent management effective.

For Hypothesis 2, One of the best achievements concerning the model developed as an outcome is the improved predictive analytics model performance to predict retention rates, R-square is 0,671 and can expound almost 67,1 percent in the variations captured by retention rates which could be determined through variance analysis. Other overall characteristics showed low generalization RMSE (0,0682) and MAE (0,0521) and, therefore, quite adequate and accurate predictions.

Predictive Analytics Usage-M was used as the predictor to show that Predictive Analytics Use-Medium is a good predictor of promotion success with evidence of positive impacts on the outcome of promotions, where B = 0,71052, p = 0,001. These findings confirm our hypothesis that predictive analytics increases the accuracy of HR outcomes.

The correlation analysis showed significant relations, that helped in testing the hypothesis 3. Retention Rate had positive moderate correlations with Training Hours, r=0,52, and Career Progression Score, r=0,57. There is a positive relationship between Performance Rating and both Training Hours: r = 0,35, r = 0,35 and Career Progression Score: r = 0,41. The results confirm this hypothesis, since specific metadata attributes are highly correlated with the current state of retention and progress at work, thereby underlining their relevance when performing talent management.

While testing the hypothesis 4, a complementing the strong performance put up by the machine learning model were key metadata attributes that saw significant coefficients in the regressions. Therefore, this exposes the value in metadata integration in predictive analytics. Improved precision in making predictions around both retention and promotion will mean better value in decision-making.

On one perspective, the model is on equal reliance with predictive analytics use since B = 0,71052, p= 0,001, allowing an evading overdependence of relying much on automated tools that result in biases in decision making. Thus, this supports the hypothesis.

Overall, the findings of this study have verified the final hypothesis. Regression and machine learning analyses were performed to show that the integration of metadata attributes such as training, performance, and career progression with predictive analytics tools yields actionable insights for retention and promotion outcomes. This shows the huge potential that organizations in Jordan have to gain by embracing data-driven approaches in their HR decision-making for optimization of talent management.

Interpretations

Whereas this relation is to be predicted as positive, the relation between Age and Retention Rate may, in turn, reveal a longer tenure and better integration within the workplace culture of older age groups, for which fewer outside career opportunities may be found. However, its smaller effect size is indicative of the factor of age being secondary to other more determining factors.

It came out that Performance Rating is a strong predictor of retention, therefore, it can be deduced that clear and fair ratings ensure employee loyalty. Correspondingly, employees with higher performing scores are likely to feel their worth and motivation to continue with the organization. Similarly, Training Hours proved to be a significant predictor, emphasizing the gravity of professional development opportunities. The positive relationship between training and retention may imply that employees perceive these investments as a sign of organizational commitment to their development.

Most of all, the strong impact of Career Progression Score on retention underlines the importance of advancement opportunities. If employees see a clear route for progression, they will be more likely to remain engaged and committed to their organizations. These findings collectively provide the strategic relevance of metadata attributes in driving employee retention.

Further, the multivariate factors that predict promotion success are many. The results indicate that age and tenure significantly predict the likelihood of promotion success, reflecting experience and organizational familiarity. Older employees and longer-tenured workers likely benefit from accumulated knowledge, established networks, and demonstrated contributions, thus positioning them as strong candidates for advancement.

Similarly, Training Hours were a significant predictor of promotion success, which overemphasizes the fact that bettering one’s skills goes hand in hand with career growth. People who undergo training programs develop their competencies but also show that they are ready for more significant tasks and challenges. On the other hand, the fact that medium levels of Predictive Analytics Usage have a positive impact on promotions implies moderate use of the analytical tool to serve better decision-making by providing enough insights to act upon, not completely on automation. This balance would appear to facilitate fair, efficient assessments of promotion candidates.

The correlation analysis brought into light the existence of significant relationships among metadata features underlining their interconnectedness with talent management. For example, the moderate correlations of Retention Rate with Training Hours and Career Progression Score suggest the interaction of development opportunities and pathways to advancement. These results show that holistic approaches toward several facets of employee experience will yield maximum benefits in retention.

Likewise, the positive associations among Performance Rating, Training Hours, and Career Progression Score indicate that the high performers tend to be those for whom the organizational investments in development have paid the most. The congruence suggests that the organization could use predictive analytics to pinpoint the high-potentials and apply special interventions on them.

Predictive Analytics and Decision Making

relationships unearthed through the statistical model found further confirmation in machine learning. The strength of this model, with 67,1 % of retention rates’ variance explained, spoke volumes for the robust metadata attributes in predicting employee outcomes. Low error rates at RMSE = 0,0682 and MAE = 0,0521 further underpin precision and reliability in predictive analytics used within the space of people management.

These findings confirm the utility of data-driven approaches in HR. Integrating such predictive tools with metadata will allow the organization to understand better predictive values of outcomes on retention and promotion for early intervention toward the attainment of organizational goals.

These results are also in tune with the larger objective of encouraging data-driven talent management practices. The study contributes to the literature with an indication that organizations in Jordan and other contexts may benefit from incorporating predictive analytics into their HR practices. Specifically, Retention can be enhanced by investing in training programs, establishing clear performance evaluation frameworks, and offering career progression opportunities. Also, promotions can be optimized by balancing experience with the development initiatives and leveraging moderate predictive analytics to ensure fair consideration.

The interplay of metadata attributes and predictive analytics draws a picture of a future with reduced biases, higher efficiencies in decision-making, and a truly equitable workplace. By addressing employee development as a holistic process and leveraging advanced analytics judiciously, the organizations have the right setting for employee satisfaction and their success.

DISCUSSION

Enhancing Retention through Metadata Integration

The significance of metadata attributes in retention is also supported by available literature, which focuses on employee growth and development as the crucial factor that can help in reduction in turnover. Several studies have established that offering opportunities for training and clear career advancement pathways nurture organizational commitment in employees.^(54,55) This also complements other research findings on the quantitative effect of training hours and career progression grades on retention rates, which simply support the fact that employees will be willing to stay when they see value in their growth.

Also consistent with the literature such as Onyeaku⁽⁵⁶⁾ and Samseer et al.⁽⁵⁷⁾ that linked them to employee satisfaction and motivation, performance ratings significantly predicted retention outcomes. Organizations, according to findings, need to install proper evaluation systems in which the employees’ contributions should be fairly appraised to guarantee the transparency of the mechanisms in the performance appraisal system recommended in human resource development literature.

Objectivity and Precision in Promotion Decisions

This finding on the role of metadata in promotion decisions supports prior research advocating for data-driven approaches in mitigating biases within talent management. For example, Pandey and Mehta⁽²⁵⁾ emphasizes the role of structured evaluations in reducing subjectivity in promotion decisions. This study extends that knowledge by incorporating factors like tenure and training hours with predictive analytics tools to show how combining employee attributes with technology can enhance the fairness and efficiency of promotions.

The finding from this is that whereas analytics can provide valuable insight into a problem, over-inclination on the technology independent of judgment undermines decisions, an aligned finding by Sharmila et al. that highlights great effects brought forth by moderate predictive analytics usage in promotion successes.⁽⁵²⁾ The delicate balance, then, between human intuition and insight forces equity and efficiency into the promotion process.

Interconnectedness of Metadata Attributes

These associations identified between metadata attributes-training hours, career progression score, and retention rate-find their roots in organizational behaviour literature. Eisenberger and Stinglhamber researched perceived organizational support and pointed out that employees who receive recognition are more likely to stay longer and be attached to the organization.⁽³¹⁾ The research underpins those conclusions, thus, it reinforces that investments in training and career progression have a dual effect on enhancing not only individual capability but also long-term organizational commitment.

Furthermore, the modest associations among performance appraisals, training hours, and career development grade support the suggestion by Ahmed et al, that better performers have a greater likelihood of receiving developmental opportunities, which become part of a virtuous cycle relating to engagement and retention.^(58,59,60)

Predictive Analytics as a Strategic Tool

These findings on predictive analytics are in agreement with the existing literature on the infusion of technology into human resource management. The study by Levenson, determined that predictive analytics hold great promise that could be actualized to optimize efficiency in decision-making by predicting such basic outcomes as retention and promotion potential.⁽²⁹⁾ Consequently, this research has ratified these claims and showed that predictions about employee outcomes can in fact be very accurate which would create an avenue for interventions.

However, the findings also caution against over-reliance on analytics and concur with critiques in the literature which raise concerns about algorithmic bias and ethical considerations.⁽⁴²⁾ Strong influence of moderate analytics usage supports an argument that technology should enhance and not replace human judgment in talent management decisions.

Implications for the Jordanian Context

Therefore, both the adaptability of predictive analytics to integrate metadata into the Jordanian context and regional studies support the proposition of the great effect that cultural and economic factors might have on shaping human resource management practices. For instance, research by Shin et al. has shown the degree to which embedded collectivist work cultures dominate employee expectations and management approaches of Middle Eastern organizations.⁽⁴³⁾ This study extends those insights to demonstrate how predictive tools, when tailored to the local contexts, can effectively solve challenges in talent management.

This research combines global principles of data-driven decision-making with local organizational dynamics and extends the emergent literature on cross-cultural applications of predictive analytics. This emphasizes the imperative need to balance advanced technology adoption with cultural-sensitive approaches in Jordanian organizations with a view to fostering employee engenderment and ensuring fairness.

Bridging Theory and Practice in Talent Management

This research connects the level of theoretical approaches to real-world applications regarding predictive analytics and metadata integration. The findings in this study support the resource-based theories of competitive advantage suggested by Barney and Wright relating to the strategic importance of the development and retention of human capital.⁽³⁸⁾ In that line, this study contributes to a higher discussion on how organization resources can be deployed towards further success by demonstrating just the practical value of a data-driven approach.

The implications also connect to the emerging discussions on workforce analytics in the Fourth Industrial Revolution. As organizations increasingly adopt predictive tools, this study highlights the need for ethical considerations and balanced implementation to maximize impact. It provides actionable insights for practitioners while reinforcing theoretical perspectives on the role of technology and metadata in shaping the future of work.

CONCLUSION

The study showed how integrating predictive analytics with metadata can transform the way talent management strategies are put together. It also looks into a few key employee attributes responsible for retention and promotion, such as hours of training, performance ratings, and career advancement opportunities. It shows how predictive tools with metadata provide actionable insights, increase the efficiency of decision-making, reduce biases, and make the talent management process fair and effective.

It also strongly emphasizes balancing data-driven approaches with human judgment for fairness and ethical integrity in decision-making. For Jordan, the adaptability of such strategies to the local organizational and cultural dynamics brings useful implications for the enhancement of human resource practices in the region. The study represents one in the growing discourse of data-driven HR management, as it offers a road map that organizations can follow in trying to align employee development with strategic goals in these increasingly competitive and technology-driven times.

REFERENCES

1. Yuan J. HR predictive data analytics in the era of big data. Proceedings of the 2018 International Conference on Economics, Business, Management and Corporate Social Responsibility (EBMCSR 2018). Atlantis Press; 2018. p. 388–390. doi:10.2991/ebmcsr-18.2018.75.

2. Alrabei AM. Green electronic auditing and accounting information reliability in the Jordanian social security corporation: the mediating role of cloud computing. Int J Financ Stud. 2023;11(3):114. doi:10.3390/ijfs11030114.

3. Alabbas MMG, Alshaboul MT, Daud D. Talent management and service quality in the Jordanian information technology companies: conceptual framework. J Hum Resour Manag. 2020;8(2):56. doi:10.11648/j.jhrm.201200802.12.

4. Jahmani A, Jawabreh O, Abokhoza R, Alrabei AM. The impact of marketing mix elements on tourist’s satisfaction towards Five Stars Hotel Services in Dubai during COVID-19. J Environ Manag Tour. 2023;14(2):335.

5. Al-Sawaie KM, Abbas NA, AlSmeiran M, Alrawashdeh H, Vasudevan A, Yaseen H, Mohammad SIS, Hunitie MF, Li Y. Estimating potential output using a production function approach. Appl Math Inform Sci. 2025;19(2):271. doi:10.18576/amis/190204.

6. Cappelli P, Keller J. Talent management: conceptual approaches and practical challenges. Annu Rev Organ Psychol Organ Behav. 2014;1(1):305. doi:10.1146/annurev-orgpsych-031413-091314.

7. Alrabei AM. The mediating effect of COVID 19—pandemic on the Nexus between accounting information systems reliability and e-commerce: from the perception of documentary credit employees. Inf Sci Lett. 2023;12(8):2867. doi:10.18576/isl/120835.

8. McConnell CR. Addressing employee turnover and retention. Health Care Manag. 2011;30(3):271. doi:10.1097/hcm.0b013e318225e3bf.

9. Allen DG, Bryant P, Vardaman JM. Retaining talent: Replacing misconceptions with evidence-based strategies. Acad Manag Perspect. 2010;24(2):48. doi:10.5465/amp.2010.51827775.

10. Ramamurthy KN, Singh M, Yu Y, Aspis J, Iames M, Peran M, Held QS. A talent management tool using propensity to leave analytics. In 2015 IEEE International Conference on Data Science and Advanced Analytics (DSAA). IEEE; 2015. p. 1–10. doi:10.1109/dsaa.2015.7344853.

11. Almomani T, Almomani M, Obeidat M, Alathamneh M, Alrabei A, Al-Tahrawi M, Almajali D. Audit committee characteristics and firm performance in Jordan: The moderating effect of board of directors’ ownership. Uncertain Supply Chain Manag. 2023;11(4):1897. doi:10.1108/GKMC-02-2024-0105.

12. Alrabei AM. The influence of accounting information systems in enhancing the efficiency of internal control at Jordanian commercial banks. J Manag Inform Decis Sci. 2021;24(1):1–9.

13. DiClaudio M. People analytics and the rise of HR: how data, analytics and emerging technology can transform human resources (HR) into a profit center. Strat HR Rev. 2019;18(2):42. doi:10.1108/shr-11-2018-0096.

14. Aladwan K, Bhanugopan R, Fish A. Managing human resources in Jordanian organizations: challenges and prospects. Int J Islamic Middle Eastern Financ Manag. 2014;7(1):126. doi:10.1108/imefm-09-2013-0104.

15. Alrabei AM, Haija AAA, Aryan LA. The mediating effect of information technology on the relationship between organizational culture and accounting information system. Int J Adv Sci Technol. 2020;29(5):1085.

16. Mohammad AAS, Al-Daoud KI, Al-Daoud SIS, Samarah TA, Vasudevan A, Li M. Content marketing optimization: A/B testing and conjoint analysis for engagement strategies in jordan. J Ecohumanism. 2024;3(7):3086. doi:10.62754/joe.v3i8.5066.

17. Leisy B, Pyron D. Talent management takes on new urgency. Compens Benefits Rev. 2009;41(4):58. doi:10.1177/0886368709334323.

18. Mohammad AAS, Al-Daoud KI, Mohammad SIS, Hindieh A, Vasudevan A, Zhou W. Analysing the effectiveness of omnichannel marketing strategies on customer experience in Jordan. J Ecohumanism. 2024;3(7):3074. doi:10.62754/joe.v3i7.5063.

19. Alrabei AM, Ababnehi DS. The moderating effect of information technology on the relationship between audit quality and the quality of accounting information: Jordanian auditors’ perception. J Theor Appl Inform Technol. 2021;99(14):3365.

20. Ribes E, Touahri K, Perthame B. Employee turnover prediction and retention policies design: a case study. arXiv. 2017. doi:10.48550/arxiv.1707.01377.

21. Tambe P, Cappelli P, Yakubovich V. Artificial intelligence in human resources management: challenges and a path forward. Calif Manag Rev. 2019;61(4):15. doi:10.1177/0008125619867910.

22. Alrabei AMA. Perception of Jordanian banks employees on the relationship between accounting information quality (AIQ) and documentary credits. Int J Appl Bus Econ Res. 2017;15(19):409.

23. Rub BSA. The role of human resource management on attracting and retaining of qualified employees in Jordan organizations. SSRN Electron J. 2010. doi:10.2139/ssrn.1600813.

24. Mohammad AAS, Alolayyan MN, Al-Daoud KI, Al Nammas YM, Vasudevan A, Mohammad SIS. Association between social demographic factors and health literacy in Jordan. J Ecohumanism. 2024;3(7):2351.

25. Pandey S, Mehta J. HRPA: Human resource prediction analytics. In 2022 Third International Conference on Intelligent Computing Instrumentation and Control Technologies (ICICICT). IEEE; 2022. p. 721–726. doi:10.1109/icicict54557.2022.9917576.

26. Darwish TK, Singh S, Mohamed AF. The role of strategic HR practices in organisational effectiveness: an empirical investigation in the country of Jordan. Int J Hum Resour Manag. 2013;24(17):3343. doi:10.1080/09585192.2013.775174.

27. Alabbas MMG, Daud D, Adnan WH. Competitive creativity between talent management and service quality: evidence from Jordan information technology sector. J Bus Manag Account. 2024;14(1):37. doi:10.32890/jbma2024.14.1.2.

28. Likhitkar P, Verma P. HR value proposition using predictive analytics: an overview. In: Likhitkar P, Verma P, editors. Advances in Intelligent Systems and Computing. Singapore: Springer Nature; 2019. p. 165–171. doi:10.1007/978-981-13-9330-3_15.

29. Levenson A. Strategic analytics: advancing strategy execution and organizational effectiveness. 1st ed. Berrett-Koehler Publishers; 2015.

30. Anderson DR, Bjarnadóttir MV, Ross DG, Perry R. Algorithm fairness. Oper Res Manag Sci. 2021. doi:10.1287/orms.2021.03.20.

31. Eisenberger, R., Stinglhamber, F. Perceived organizational support: fostering enthusiastic and productive employees. In: Eisenberger R, Stinglhamber F, editors. American psychological association eBooks. American Psychological Association; 2011. doi:10.1037/12318-000.

32. Aguwamba, S., Chukwu, B. A., & Ezeabogu, A. N. (2019). Empirical investigation of the relationship between career progression and employee turnover intention. Am J Soc Sci Humanit. 4(4), 581. doi:10.20448/801.44.581.591.

33. Davenport, T., Harris, J. Competing on analytics: The new science of winning. Choice Reviews Online. 2007;44(11):44. doi:10.5860/choice.44-6322

34. Binns R. Human judgment in algorithmic loops: individual justice and automated decision‐making. Regul Gov. 2020;16(1):197. doi:10.1111/rego.12358.

35. Al‐Husan FB, ALHussan FB, Perkins SJ. Multilevel HRM systems and intermediating variables in MNCs: longitudinal case study research in Middle Eastern settings. Int J Hum Resour Manag. 2013;25(2):234. doi:10.1080/09585192.2013.826912.

36. Bohnet I, Bazerman MH, van Geen A. When performance trumps gender bias: joint versus separate evaluation. SSRN Electron J. 2012. doi:10.2139/ssrn.2087613.

37. Kumar JR, Kalnawat A, Pawar AM, Jadhav VD, Srilatha P, Khetani V. Transparency in algorithmic decision-making: interpretable models for ethical accountability. E3S Web Conf. 2024;491:2041. doi:10.1051/e3sconf/202449102041.

38. Barney JB, Wright PM. On becoming a strategic partner: The role of human resources in gaining competitive advantage. Hum Resour Manag. 1998;37(1):31. doi:10.1002/(sici)1099-050x(199821)37:1<31::aid-hrm4>3.0.co;2-w.

39. Nurimansjah RA. Dynamics of human resource management: Integrating technology, sustainability, and adaptability in the modern organizational landscape. Golden Ratio Mapping Idea Lit Format. 2023;3(2):104. doi:10.52970/grmilf.v3i2.324.

40. Al-Dmour R, Love S, Al‐Debei MM. Measuring the effectiveness of HRIS practice in business organisations: a study in the context of a developing country. Int J Bus Innov Res. 2015;9(5):507. doi:10.1504/ijbir.2015.071594.

41. Ameer F, Khan NR. National culture, employee’s engagement and employee’s CSR perceptions in technology based firms of Pakistan. J Manag Sci. 2019;6(2):54. doi:10.20547/jms.2014.1906205.

42. Eisenberger R, Shanock LR, Wen X. Perceived organizational support: why caring about employees counts. Annu Rev Organ Psychol Organ Behav. 2019;7(1):101. doi:10.1146/annurev-orgpsych-012119-044917.

43. Shin D, Chotiyaputta V, Zaid B. The effects of cultural dimensions on algorithmic news: How do cultural value orientations affect how people perceive algorithms? Comput Hum Behav. 2021;126:107007. doi:10.1016/j.chb.2021.107007.

44. Poisat P, Mey MR, Sharp GD. Do talent management strategies influence the psychological contract within a diverse environment? SA J Hum Resour Manag. 2018;16. doi:10.4102/sajhrm.v16i0.1044.

45. Kroese I. Is employee training really gender-neutral? Introducing a sex/gender-sensitive model of training. Hum Resour Manag Rev. 2022;32(4):100890. doi:10.1016/j.hrmr.2021.100890.

46. Wöcke A, Heymann M. Impact of demographic variables on voluntary labour turnover in South Africa. Int J Hum Resour Manag. 2012;23(16):3479. doi:10.1080/09585192.2011.639028.

47. Patro CS. A study on the impact of employee retention policies on organisation productivity in private sector. Int J Asian Bus Inf Manag. 2014;5(3):48. doi:10.4018/ijabim.2014070104.

48. Canedo JC, Graen GB, Grace M, Johnson RD. Navigating the new workplace: technology, millennials, and accelerating HR innovation. AIS Trans Hum Comput Interact. 2017;9(3):243. doi:10.17705/1thci.00097.

49. Rawabdeh M, Nawafleh S. The impact of economic decline on the satisfaction and productivity of the public employees in the Jordanian public-sector. Int J Product Qual Manag. 2019;1(1):1. doi:10.1504/ijpqm.2019.10020857.

50. Gurusinghe RN, Arachchige BJH, Dayarathna NWKD. Predictive HR analytics and talent management: a conceptual framework. J Manag Anal. 2021;8(2):195. doi:10.1080/23270012.2021.1899857.

51. Simbeck K. HR analytics and ethics. IBM J Res Dev. 2019;63(4):9. doi:10.1147/jrd.2019.2915067.

52. Sharmila K, Devi R, Shanthi C. Review on latest trends and techniques in predictive analytics. Int J Res Appl Sci Eng Technol. 2022;10(12):1762. doi:10.22214/ijraset.2022.48223.

53. Mahendran C, Krithika M. Exploring the organizational factors hindering the HR analytics adoption in manufacturing industries. 2024 11th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO). IEEE; 2024. p. 1–6. doi:10.1109/icrito61523.2024.10522258.

54. Achim N, Mohsin FH, Ismail N. Employee commitment: through training opportunities and organization compensation system. Adv Bus Res Int J. 2020;6(2):81. doi:10.24191/abrij.v6i2.10312.

55. Mohammad AAS, Khanfar IA, Al-Daoud KI, Odeh M, Mohammad SI, Vasudevan A. Impact of perceived brand dimensions on consumers’ purchase choices. J Ecohumanism. 2024;3(7):2341.

56. Onyeaku J. How can organizations effectively use appraisal systems to retain knowledge workers? A systematic review of the literature. Muma Bus Rev. 2020;4:157. doi:10.28945/4603.

57. Samseer RH, Bamini J, Priyadharsini R, Vasudevan A, Parahakaran S, Krishnasamy HN, Mohammad SI, Alshurideh MT. A new conceptualization of self as an energetic node in cultural dynamics: transitioning from classical theories to complex systems. Appl Math Inf Sci. 2025;19(2):259. doi:10.18576/amis/190203.

58. Ahmed U, Kura KM, Umrani WA, Pahi MH. Modelling the link between developmental human resource practices and work engagement: The moderation role of service climate. Glob Bus Rev. 2019;21(1):31. doi:10.1177/0972150919837813.

59. Mohammad AA, Shelash SI, Saber TI, Vasudevan A, Darwazeh NR, Almajali R. Internal audit governance factors and their effect on the risk-based auditing adoption of commercial banks in Jordan. Data Metadata. 2025;4:464. doi:10.56294/dm2025464.

60. Alrabei AM, Al-Othman LN, Al-Dalabih FA, Taber TA, Ali BJ, Amareen SAM. The impact of mobile payment on the financial inclusion rates. Inform Sci Lett. 2022;11(4):1033. doi:10.18576/isl/110404.

61. Alrabei AM, Al-Othman LN, Abutaber TA, Alathamneh MS, Almomani TM, Qeshta MH, Amareen SAM. Nexus between intellectual capital and financial performance sustainability: evidence from listed Jordanian firms. Appl Math. 2023;17(5):881. doi:10.18576/amis/170514.

62. Alrabei AM, Jawabreh O, Abdullah Saleh MM. Accounting information and its role in financial reports quality in Jordanian hotels, and social performance as a mediating effect. Int J Sustain Dev Plan. 2023;18(7):2271. doi:10.18280/ijsdp.180732.

FUNDINGS

None.

CONFLICT OF INTEREST

None.

AUTHORSHIP CONTRIBUTION

Conceptualization: Anber Abraheem Shlash Mohammad, Suleiman Ibrahim Mohammad, Badrea Al Oraini, Ayman Hindieh, Asokan Vasudevan, Mohammad Faleh Ahmmad Hunitie, Hongli Long, Imad Ali.

Research: Anber Abraheem Shlash Mohammad, Suleiman Ibrahim Mohammad, Badrea Al Oraini, Ayman Hindieh, Asokan Vasudevan, Mohammad Faleh Ahmmad Hunitie, Hongli Long, Imad Ali.

Writing – original draft: Anber Abraheem Shlash Mohammad, Suleiman Ibrahim Mohammad, Badrea Al Oraini, Ayman Hindieh, Asokan Vasudevan, Mohammad Faleh Ahmmad Hunitie, Hongli Long, Imad Ali.

Writing – proofreading and editing: Anber Abraheem Shlash Mohammad, Suleiman Ibrahim Mohammad, Badrea Al Oraini, Ayman Hindieh, Asokan Vasudevan, Mohammad Faleh Ahmmad Hunitie, Hongli Long, Imad Ali.