Abstract
In the field of recruitment and human resources management, the problem arises of automatization of the assessment process of the characteristics of human capital, taking into account, among other things, the personality characteristics of the employee. The article is devoted to the problem of identification of such characteristics that have the greatest contribution to some indicators of the effectiveness of an employee of an organization with self-reported data on professional skills and answers to questions–statements about various psychological aspects of personality. The general structure of the survey tools based on self-reports of employees is proposed, as well as the formalization of the proposed methods of data analysis. The cluster analysis was used for the identification of groups with similar professional skills. Special psychometric scales based on the questions–statements are selected and analyzed via the item response theory approach, giving the estimates of the latent variable, that reflects personal characteristics. At the final stage of the study, the relationship between the estimated factors (identified clusters and estimated latent variables) and the indicator of employee effectiveness was assessed. As such indicator, the fact of a managerial position was used. The proposed approach is a structure of a pilot study that allows to identify the characteristics of human capital (professional skills and personality traits) that have the greatest contribution to the performance indicators of an employee or organization, and is aimed at reducing labor costs at subsequent stages of a more detailed and targeted study. The possibilities of the proposed approach are demonstrated with data collected among state civil servants in Russia. The fact of having a managerial position is used as an indicator of effectiveness.
Subject
Artificial Intelligence,Applied Mathematics,Computational Theory and Mathematics,Computational Mathematics,Computer Networks and Communications,Information Systems
Reference44 articles.
1. Dastile X., Celik T., Potsane M. Statistical and machine learning models in credit scoring: A systematic literature survey // Applied Soft Computing. 2020. vol. 91. pp. 106263.
2. Djeundje V.B., Crook J., Calabrese R., Hamid M. Enhancing credit scoring with alternative data // Expert Systems with Applications. 2021. vol. 163. pp. 113766.
3. Абрамов М.В., Тулупьева Т.В., Тулупьев А.Л. Социоинженерные атаки: социальные сети и оценки защищенности пользователей. СПб.: ГУАП, 2018. 266 с.
4. Олисеенко В.Д., Абрамов М.В., Тулупьев А.Л., Иванов К.А. Прототип программного комплекса для анализа аккаунтов пользователей социальных сетей: веб-фреймворк Django // Программные продукты и системы. 2022. Т. 35. № 1. С. 45–53. doi: 10.15827/0236-235X.137.
5. Khlobystova A., Korepanova A., Maksimov A., Tulupyeva T. An Approach to Quantification of Relationship Types between Users Based on the Frequency of Combinations of Non-numeric Evaluations // Proceedings of the Fourth International Scientific Conference “Intelligent Information Technologies for Industry” (IITI’19). Advances in Intelligent Systems and Computing. 2020. vol. 1156. pp. 206—213.