Selection of Informational Signs for Forecasting Employment of Graduates
УДК 519.67 +004.852
Abstract
The article is devoted to solving the problem of forming the space of information signs for the model of forecasting the employment of graduates by their progress. Several variants of the recognition space were formed using different methods of automated selection of information signs. The evaluation of the informativeness of the signs is understood as determining the extent of their impact on the level of the potential of labor activity of graduates of the university and job applicants.The effectiveness of the methods of automated selection of information features was determined empirically: on the generated samples, training experiments were carried out using gradient boosting and random forests.The greatest accuracy of the forecast was achieved in the formation of the recognition space by means of one-dimensional selection and training by the method of random forests. The results obtained can be used in the development of an automated information system for assessing the potential of work activity of graduates and job applicants.
Downloads
Metrics
References
Мутанов Г.М., Мамыкова Ж.Д., Бобров Л.К. Роль и место дата-центра в ИТ-инфраструктуре университета // Вестник НГУ Серия : Информационные технологии. 2014. Т. 12. Вып. 2.
Федотов А.М. и др. Концептуальная модель научно-образовательной информационной системы // Вестник НГУ. Серия : Информационные технологии. 2015. Т. 13. Вып. 3.
Смыкова Н.В., Авдеев А.С., Томашев М.В. Отбор информативных признаков для прогнозирования трудоустройства выпускников вуза // Наука и бизнес: пути развития. 2018. № 12 (90).
Паклин Н.Б., Орешков В.И. Бизнес-аналитика: от данных к знаниям. СПб., 2013.
Мюллер А. Введение в машинное обучение с помощью Python : руководство для специалистов по работе с данными. М., 2017.
Николенко С., Кадурин А., Архангельская Е. Глубокое обучение. СПб., 2018.
Таскин А.С. Тест обобщающей способности линейных методов прогнозирования // Вестник НГУ Серия : Информационные технологии. 2013. Т. 11. Вып. 2.
Анисимов Д.С., Рязанов М.А., Шаповал А.И. Подход к обработке многомерных данных пептидных микрочипов // Известия Алт. гос. ун-та. 2015. № 1/2(85).
Ketkar N. Deep Learning with Python: A Hands-on Introduction. Bangalore, Karnataka, India. 2017.
Scikit-learn. Machine Learning in Python. URL: http:// scikit-learn.org/stable.
Пальчунов Д.Е., Яхъяева Г.Э. Нечеткие логики и теория нечетких моделей // Алгебра и логика. 2015. T. 54. № 1.
Большакова Е.И. и др. Автоматическая обработка текстов на естественном языке и компьютерная лингвистика. М., 2011.
Izvestiya of Altai State University is a golden publisher, as we allow self-archiving, but most importantly we are fully transparent about your rights.
Authors may present and discuss their findings ahead of publication: at biological or scientific conferences, on preprint servers, in public databases, and in blogs, wikis, tweets, and other informal communication channels.
Izvestiya of Altai State University allows authors to deposit manuscripts (currently under review or those for intended submission to Izvestiya of Altai State University) in non-commercial, pre-print servers such as ArXiv.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (CC BY 4.0) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
