See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/372410450

Exploring human resource management intelligence practices using machine

learning models

Article in The Journal of High Technology Management Research · July 2023

DOI: 10.1016/j.hitech.2023.100466

CITATIONS READS

2 485

5 authors, including:

Siripuri Kiran Narasimha Reddy Soora

Kakatiya Institute of Technology and Science Kakatiya Institute of Technology and Science
55 PUBLICATIONS 313 CITATIONS 31 PUBLICATIONS 134 CITATIONS

SEE PROFILE SEE PROFILE

Kumar Dorthi
Kakatiya Institute of Technology and Science
14 PUBLICATIONS 23 CITATIONS

SEE PROFILE

All content following this page was uploaded by Siripuri Kiran on 18 July 2023.

The user has requested enhancement of the downloaded file.

 Journal of High Technology Management Research 34 (2023) 100466

Contents lists available at ScienceDirect

Journal of High Technology Management Research

journal homepage: www.elsevier.com/locate/hitech

Exploring human resource management intelligence practices

using machine learning models
Sai Rama Krishna Indarapu a, *, Swathy Vodithala a, Naveen Kumar b, Siripuri Kiran a,
Soora Narasimha Reddy a, Kumar Dorthi a
a
Department of CSE(Networks), Kakatiya Institute of Technology and Science, Warangal, Telangana, India
b
Amity Institute of Information Technology, Amity University, Patna, India

A R T I C L E I N F O A B S T R A C T

Keywords: The use of machine learning for recruitment has become one of the main themes in human re­
HR intelligent practices sources ever since machine learning software investigated the first recruitment software and
Business management discovered that utilizing technology improves their effectiveness at work, speed, and makes the
Machine learning
process simpler. In order to better handle employee files, profiles, turnover, data analytics, and
the creation of electronic personal data sheets for government service records, a human resource
information system that incorporates machine learning has been created. Using a supervised
machine learning technique, it was designed to foresee staff turnover. From a theoretical
perspective, machine learning apps may be able to perform the same tasks as HR specialists, if not
better or faster. Supporting HR professionals in becoming a true business partner and providing
them with accurate and reliable advice, the interaction between HR professionals and line top
management believes that the HR professionals still has surplus over machine learning, alone.
Human resources methods and the significance of machine learning are the primary focus of this
paper. This paper's three goals are to (1) determine how much of an impact Machine learning can
have on the organization's recruitment procedures, (2) examine the extent to which this tech­
nology has been adopted, and (3) examine the frequency with which complaints have been
lodged during these crucial exercises.

1. Introduction

Occupational health psychology, positive psychology, wellbeing, organizational psychology, positive organizational behavior, and
similar subjects have become commonplace in modern businesses thanks to advances in technology. Positive human resource strengths
and psychological capacities that can be managed, measured, and developed to enhance performance in complex work environments
are the primary emphasis of these academic disciplines (Morton, Michaelides, Roca, & Wagner, 2019). Intelligence which includes the
ability to understand, manage and regulate emotions in self and others, Organizational Commitment that guarantees the commitment
of employees towards an organization and Work Engagement that ensures the engagement of employees in the assigned duties are
leading topics in these fields that helps in creating positive and healthy work environments (Bin Ahmad & Jasimuddin, 2021). The
mental healthcare industry could benefit from more cutting-edge HR policies and strategies, so this research attempts to analyze how

* Corresponding author.
E-mail addresses: [email protected] (S.R.K. Indarapu), [email protected] (N. Kumar), [email protected] (S. Kiran), [email protected]
(S.N. Reddy), [email protected] (K. Dorthi).

https://doi.org/10.1016/j.hitech.2023.100466
Received 18 March 2023; Received in revised form 29 April 2023; Accepted 18 June 2023
Available online 14 July 2023
1047-8310/© 2023 Elsevier Inc. All rights reserved.
S.R.K. Indarapu et al. Journal of High Technology Management Research 34 (2023) 100466

these new areas of study can be applied in the field.

Intelligence is the capacity to learn from and act on one's own and other people's emotional experiences. Many fields, including
business and human resource management, are related to EI because it is viewed as a psychological concept (Choi, Ravichandran, &
O'Connor, 2019). The word “Intelligence” was first used in print by Peter Salovey and John Mayer. Initially, they thought of EI as “a
form of intelligence that involves the ability to monitor one's own and other people's feelings and emotions, to discriminate among
them, and to use this information to guide one's thinking and actions.” (Salovey and Mayer, 1990). However, this is a popular field of
research in industrial psychology, which focuses on human capital and its capabilities (Liu, Wu, & Wang, 2020). The EI principle is
seen as an effective tool to evaluate and understand people's attitudes, behavior, management styles, and interpersonal skills; thus, it is
becoming increasingly pertinent to all HR practices. Recruitment, selection, planning, management development, client relations, and
training are just some of the many HR procedures that take it into consideration.
Machine learning (ML) has the potential to significantly improve the recruitment process for businesses by making it more efficient,
effective, and objective. Here are some ways in which ML can improve the hiring process:
Candidate Sourcing: Machine learning can assist sift through a sea of resumes to find the ones that really stand out as the best fit
for an open position. It can also be used to find “passive candidates,” or those who aren't actively seeking work but would be a good fit
for the company.
Resume Screening: To find the best candidates for an open position, ML can examine their application materials such resumes and
cover letters. It can also help to eliminate potential screening biases, leading to a more objective evaluation of applicants.
Candidate Assessment: The results of tests and interviews can be analyzed with ML to determine who is the best fit for an open
position. HR will be able to ask more specific questions of candidates based on any trends or patterns that are uncovered.
Candidate Matching: ML can be used to find the best possible candidates for open positions by taking into account their relevant
abilities, work history, and educational background. Candidates that show promise for several positions within the company can be
uncovered in this way as well.
Time and Cost Savings: The recruitment process can be automated with the use of ML to save time and money by screening
resumes and matching candidates.
When used to the recruitment process, ML can help businesses find the best possible employees, eliminate prejudices, and cut down
on costs. In order to prevent unexpected biases or discriminatory behaviors, however, it is crucial that the ML algorithms be open and
ethical.

2. HR intelligent practices using machine learning

It's certain that machine learning will propel the human resources sector to new heights. Companies like JP Morgan have used it to
root out bad apples in the workforce, and LinkedIn use it to better match job applicants with available positions. However, there are
some fundamental privacy concerns that must be addressed before HR can fully shift its focus to strategy. Concerns have long been
raised about the morality of employing AI in human resources (HR) and employees' private information for commercial expansion.
Therefore, before implementing machine learning solutions, businesses must establish a legal framework that safeguards employee
data privacy within the organization. Machine learning also makes predictions based on historical data. In order to guarantee the
accuracy of the predictions your algorithms make, they must be regularly updated. Once machine learning has been implemented,
businesses will be free to concentrate on disruptive factors like innovation and new technologies.
The application of machine learning to HR intelligent practices entails making use of algorithms and predictive analytics with the
aim of enhancing HR performance and results (Hussain et al., 2022). Some intelligent HR methods that make use of machine learning
include the following:
Recruitment and Talent Acquisition: Resumes, employment postings, and candidate information can all be analyzed by machine
learning algorithms to determine who is the best fit for an open position. Time-to-hire is decreased and recruitment outcomes are
enhanced because the algorithms can analyze the data to forecast which applicants are most likely to accept an offer.
Employee Retention: Data on employees, such as their work performance and responses to surveys about their job satisfaction,
can be analyzed by machine learning algorithms to predict which workers might be leaving the business. Human resources managers
can use this information to create tailored retention strategies that engage key personnel and cut attrition.
Performance Management: Patterns and trends in employee performance data can be analyzed by machine learning algorithms to
reveal where workers could benefit from additional coaching or guidance. Human resource administrators can use this information to
better understand how to motivate and engage their workforce.
Employee Engagement: Factors that increase employee involvement can be determined by using machine learning algorithms to
examine data gathered from employee surveys, social media, and other sources. Human resource managers can use this information to
better involve their workforce and boost morale.
Predictive Analytics: Machine learning algorithms can analyze past information to make predictions about the future, such as
which workers are more likely to quit and which candidates are more likely to be successful in a given position. Human resource
administrators can use this information to take preventative measures.
Overall, machine learning-based intelligent HR practices allow HR managers to make better choices, boost HR performance, and
increase employee and company satisfaction.
First and foremost among early machine learning applications is applicant monitoring and assessment, especially for firms and roles
that receive many applications. Glint is not an AI firm, but it does employ AI tools to help businesses cut costs and improve employee
satisfaction. Human resources and management can benefit from machine learning software by keeping track of candidates as they

2
S.R.K. Indarapu et al. Journal of High Technology Management Research 34 (2023) 100466

move through the interview process and providing more timely, actionable feedback to job seekers. Peoplise is another option for
helping businesses determine a candidate's fit score by integrating the results of digital screening and online interviews. A CEB essay on
utilizing machine learning to reduce prejudice warns that human oversight is still of crucial significance, despite the fact that
competition for the finest individuals has prompted many HR departments to utilize algorithm-based assessments.

3. Applications of machine learning techniques in HR management

Human resource management is just one field that is seeing an uptick in the use of machine learning methods (Kakkavas, Tsitseklis,
Karyotis, & Papavassiliou, 2020). Below are some examples of how machine learning is being used in human resource management:
Acquiring and Recruiting New Employees: Algorithms trained on large amounts of data can read and interpret job postings, ap­
plications, and cover letters to find the most qualified applicants (Arrive, Mei, Li, Yan, & Kusse, 2019). Recruiting the best possible
employees in a shorter amount of time is a huge time and money saver for HR departments.
Employee Retention: Data collected through employee surveys and performance reviews can be analyzed by machine learning
algorithms to reveal trends that may indicate which workers are most likely to leave the business (Abdelsadek, Gadallah, & Ahmed,
2019; Hamid et al., 2020; Jarrett, Blake, & Saleh, 2018; Singh, Del Giudice, Tarba, & De Bernardi, 2022; Zhao et al., 2017). Human
resources managers can use this information to take preventative measures to keep their best workers.
Performance Management: Algorithms trained on large amounts of data can look for patterns in employees' performance that
might suggest they need more guidance or training. Human resource professionals can use this information to improve their perfor­
mance management techniques.
Employee Engagement: Factors that increase employee involvement can be determined by using machine learning algorithms to
examine data gathered from employee surveys, social media, and other sources. Human resource professionals can use this information
to better involve their staff and boost morale.
Diversity and Inclusion: Data from job postings, resumes, and employee questionnaires can be analyzed by machine learning
algorithms to reveal potential gaps in an organization's diversity and inclusion initiatives (Atawia, Abou-zeid, Hassanein, & Noureldin,
2016). Human resources professionals can use this information to improve their methods for recruiting and retaining a multicultural
staff.
HR Strategies: As a whole, machine learning methods can aid HR professionals in developing more successful HR strategies,
increasing employee happiness and loyalty, and boosting productivity (Ahmed et al., 2023). There are numerous ways in which HR
methods are altered by machine learning. Some examples of how machine learning is changing human resources are as follows:
Data-driven Decision Making: When applied to large datasets, machine learning systems can spot trends and patterns that
humans might miss. Human resource managers can improve their methods in recruitment, employee engagement, performance
management, and more by adopting a data-driven strategy.
Personalization: Human resource (HR) strategies can be tailored to each employee by analyzing their performance records,
training documents, and even their own tastes using machine learning algorithms. A machine learning algorithm, for instance, could
provide guidance on appropriate professional development opportunities for a given worker on the basis of their prior success and their
desired future roles.
Automation: Many human resources processes can be automated with the help of machine learning algorithms, including the
screening of resumes, the scheduling of interviews, and the dispatching of follow-up emails. In doing so, technology frees up HR
managers' time for more strategic and interpersonal work with their staff.
Predictive Analytics: Machine learning algorithms can analyze past information to make predictions about the future, such as
which workers are more likely to quit and which candidates are more likely to be successful in a given position. With the help of this
predictive analytics method, HR managers can take preventative measures to avoid issues in the first place.
Improved Efficiency: Human resources departments can benefit from machine learning algorithms because they analyze data
more swiftly and precisely than humans (Lee, 2023). The enhanced effectiveness of human resources can reduce costs and boost
productivity.
Machine learning has a broad impact on HR practices because it helps HR managers make better choices, tailor HR strategies to
individual employees, automate routine tasks, apply predictive analytics, and boost productivity. Over the past few years, businesses
have increasingly used machine learning models to automate and enhance their hiring procedures. While machine learning models
have been successfully implemented in some areas of recruitment, their use has also been met with challenges and raised some
concerns. The limitation of machine learning models is that their accuracy depends on the quality of the training data. The model's
predictions can be inaccurate or discriminatory if it was trained with flawed or missing data. This has prompted worries that machine
learning models may be used to further institutionalize discrimination and bias in the hiring process. Another difficulty arises when
machine learning models are not transparent, making it hard for applicants to know why they were or were not chosen for a position.
Frustration and distrust in the hiring process may result.
Therefore, there have been some criticisms of employing machine learning models in the hiring process. These concerns range from
lack of openness and accountability to allegations of bias and discrimination. Keep in mind, though, that not all ML models are made
equal. Machine learning models have been effectively deployed in the recruitment processes of some companies, leading to enhanced
efficiency and more objective decision making. Although there have been some worries and complaints about the use of machine
learning models in recruitment as a whole, it is essential to assess each implementation separately. It is important for businesses to take
precautions to ensure that the models they use are honest and fair, and to have a plan in place to address any complaints or concerns
that may occur during the hiring process.

3
S.R.K. Indarapu et al. Journal of High Technology Management Research 34 (2023) 100466

Table 1
Employee training and employability as intelligent HR practice based on survey.
Dimension Survey 1 Survey 2

Tasks 0.470 0.487

Competencies 0.435 0.435
Responsibility 0.470 0.408
Value Creation 0.511 0.628

Fig. 1. Flowchart for intelligent HR practices.

4. Discussion

There are many ways in which human resource management (HRM) can benefit from the implementation of machine learning (ML)
technologies:
Increased Efficiency: Many of the tasks associated with human resource management (HRM) can be automated and streamlined
with the help of ML. Human resources departments can benefit from this since it can facilitate smoother operations, lessen admin­
istrative loads, and conserve resources.
Improved Decision-Making: By analyzing massive amounts of data and spotting patterns or trends that may not be immediately
obvious to human analysts, ML can aid HR departments in making more educated and objective judgments. Better outcomes for the
company and its workers may result from the elimination of biases and blunders in decision-making.
Better Talent Management: By analyzing data on employee performance, engagement, and other criteria to discover possibilities
for development and advancement, ML may assist HR departments in identifying and retaining top talent. Better company outcomes
may result from increased employee happiness and loyalty.
Predictive Analytics: With the use of ML, HR departments can foresee problems like employee turnover and absenteeism and take
preventative measures. This has the potential to boost productivity, cut down on HR-related expenses, and decrease employee
turnover.
Improved Employee Experience: By analyzing data on employee preferences and behaviors, ML may assist HR in customizing HR
programs and services to match the unique requirements of each employee. As a result, this has the potential to boost morale and
productivity in the workplace.
The usage of ML technology in HRM can be beneficial if done so with integrity and openness. Organizations that embrace ML with
forethought and strategy stand a better chance of realizing its potential benefits in areas such as efficiency, decision-making, talent
management, and employee experience.
To discover how the rise of the machine learning cloud will affect the HR profession, 21 experts were interviewed over the course of
10 interviews. Tasks, duties, competencies, and value creations were the four main points of discussion during the interviews. Experts
were found to have difficulty addressing these issues separately. Two surveys' inputs were based on a final selection of 86 statements
that were evenly distributed across the four dimensions.
Table 1 provides some initial insight into how specialists anticipate HR specialists' roles shifting as a result of advances in machine
learning. In this section, we only display the most recently cited claims. A statement that is only brought up once or twice during the

4
S.R.K. Indarapu et al. Journal of High Technology Management Research 34 (2023) 100466

Fig. 2. HR intelligent practices using machine learning.

Fig. 3. Applications of machine learning techniques in HR management.

conversations may be seen as less likely to occur. These statements may or may not reflect a likely future situation; however, they may
surface during the survey. As a consequence, we have a 71% response rate, which is in line with what was recommended by sumsion.
The degree of agreement between the two sets of experts determines whether or not their perspectives should be combined. When all of
the experts' views are combined, there appears to be an improvement in the response stability over two rounds. This is probably due to
the fact that the influence of individual deviations is reduced with a bigger sample size (n = 16 as opposed to n = 8 and n = 7). (See
Figs. 1–5.)
Training workers to be more marketable is a smart HR practice, as depicted in Fig. 6. Actually, they've bumped up the annual
allotment of instruction time from 18 h in 2019 to 23 h in 2023. In addition, the commitment rate of employees is 84% in 2019, with a
goal of 80% or higher by 2023, indicating high levels of employment engagement.

5. Conclusion

Success in business is a direct result of employees' training and education. Improvement of organizational, team, and individual
performance relative to established norms and standards is generally seen as the ultimate goal. Human resource management is
concerned with fostering productive relationships between companies and their existing and potential employees. The state-of-the-art
developments in machine learning are quickly becoming the norm. Because of this, businesses and individuals all over the world have
adapted their strategies for using cutting-edge technologies. Protecting sensitive human resources information is a major obstacle for
AI research and development. The administration of AI-driven HR interventions necessitates the establishment of proper governance
norms and the protection of employee data. The rules should cover not only the general technological and data entry operations, but

5
S.R.K. Indarapu et al. Journal of High Technology Management Research 34 (2023) 100466

Fig. 4. Four-dimension model.

Fig. 5. Plot for employee training and employability as intelligent HR practice based on survey.

also the various legal considerations involved. With workers hopeful and enthusiastic about the implementation of Machine learning
-based systems, the traditional role of machines in human resources is being rethought. Only the effect of machine learning on HR
workers' duties was studied here. In future studies, however, it would be prudent to avoid a narrow focus on machine learning ap­
plications in and of themselves. It's reasonable to anticipate that the full breadth of technological possibilities will have an even more
profound effect on human resources functions and occupations. Overall, ML may aid HR in seeing patterns or trends in HR data, which
can then be used to influence better strategy. However, it is crucial to use ML in an honest and open manner, and to check that no
discriminatory or biased outcomes result from the process.

CRediT authorship contribution statement

Sai Rama Krishna Indarapu: Conceptualization, Methodology, Software. Swathy Vodithala: Data curation, Writing – original
draft. Naveen Kumar: Visualization, Investigation. Siripuri Kiran: Supervision. Soora Narasimha Reddy: Software, Validation.
Kumar Dorthi: Writing – review & editing.

6
S.R.K. Indarapu et al. Journal of High Technology Management Research 34 (2023) 100466

Fig. 6. HR intelligent practices as per the survey.

Data availability

No data was used for the research described in the article.

References

Abdelsadek, M. Y., Gadallah, Y., & Ahmed, M. H. (2019). Matching-based resource allocation for critical MTC in massive MIMO LTE networks. IEEE Access, 7,
127141–127153. https://doi.org/10.1109/ACCESS.2019.2939120
Ahmed, R. R., Akbar, W., Aijaz, M., Channar, Z. A., Ahmed, F., & Parmar, V. (2023). The role of green innovation on environmental and organizational performance:
Moderation of human resource practices and management commitment. Heliyon, 9(1), Article e12679. ISSN 2405-8440, https://doi.org/10.1016/j.heliyon.2022.
e12679. ISSN 2405-8440,.
Arrive, J. T., Mei, F., Li, X. Y., Yan, Y., & Kusse, G. G. (Dec. 2019). Multinational management strategies of expatriate and local managers. IEEE Engineering Management
Review, 47(4), 39–48, 1 Fourthquarter https://doi.org/10.1109/EMR.2019.2939729, 1 Fourthquarter.
Atawia, R., Abou-zeid, H., Hassanein, H. S., & Noureldin, A. (May 2016). Joint chance-constrained predictive resource allocation for energy-efficient video streaming.
IEEE Journal on Selected Areas in Communications, 34(5), 1389–1404. https://doi.org/10.1109/JSAC.2016.2545358
Bin Ahmad, K. Z., & Jasimuddin, S. M. (March 2021). The linkage between communication satisfaction, human resources management practices, person-organization
fit, and commitment: Evidence from Malaysia. IEEE Transactions on Professional Communication, 64(1), 23–37. https://doi.org/10.1109/TPC.2020.3047428
Choi, B., Ravichandran, T., & O’Connor, G. C. (Nov. 2019). Organizational conservatism, strategic human resource management, and breakthrough innovation. IEEE
Transactions on Engineering Management, 66(4), 529–541. https://doi.org/10.1109/TEM.2018.2845343
Hamid, M., et al. (2020). An intelligent recommender and decision support system (IRDSS) for effective Management of Software Projects. IEEE Access, 8,
140752–140766. https://doi.org/10.1109/ACCESS.2020.3010968
Hussain, W., et al. (1 May 2022). Human values in software engineering: Contrasting case studies of practice. IEEE Transactions on Software Engineering, 48(5),
1818–1833. https://doi.org/10.1109/TSE.2020.3038802
Jarrett, J., Blake, M. B., & Saleh, I. (1 ). Crowdsourcing, mixed elastic systems and human-enhanced computing–a survey. IEEE Transactions on Services Computing, 11
(1), 202–214. https://doi.org/10.1109/TSC.2017.2674662
Kakkavas, G., Tsitseklis, K., Karyotis, V., & Papavassiliou, S. (June 2020). A software defined radio cross-layer resource allocation approach for cognitive radio
networks: From theory to practice. IEEE Transactions on Cognitive Communications and Networking, 6(2), 740–755. https://doi.org/10.1109/TCCN.2019.2963869
Lee, J. (2023). The era of Omni-learning: Frameworks and practices of the expanded human resource development. Organizational Dynamics, 52(1), Article 100916.
ISSN 0090-2616, https://doi.org/10.1016/j.orgdyn.2022.100916. ISSN 0090-2616,.
Liu, Y., Wu, W., & Wang, Y. (2020). The impacts of technology management on product innovation: The role of technological capability. IEEE Access, 8,
210722–210732. https://doi.org/10.1109/ACCESS.2020.3038927

7
S.R.K. Indarapu et al. Journal of High Technology Management Research 34 (2023) 100466

Morton, S., Michaelides, R., Roca, T., & Wagner, H. (Nov. 2019). Increasing employee engagement in organizational citizenship Behaviors within continuous
improvement programs in manufacturing: The HR link. IEEE Transactions on Engineering Management, 66(4), 650–662. https://doi.org/10.1109/
TEM.2018.2854414
Singh, S. K., Del Giudice, M., Tarba, S. Y., & De Bernardi, P. (Dec. 2022). Top management team shared leadership, market-oriented culture, innovation capability, and
firm performance. IEEE Transactions on Engineering Management, 69(6), 2544–2554. https://doi.org/10.1109/TEM.2019.2946608
Zhao, W., et al. (June 2017). A human-Centered activity tracking system: toward a healthier workplace. IEEE Transactions on Human-Machine Systems, 47(3), 343–355.
https://doi.org/10.1109/THMS.2016.2611825

View publication stats