Araştırma Makalesi
BibTex RIS Kaynak Göster

Personel İş Zekası Sistemi ve Veri Madenciliği ile Personel Memnuniyetinin Ölçülmesi

Yıl 2020, Ejosat Özel Sayı 2020 (ISMSIT), 323 - 334, 30.11.2020
https://doi.org/10.31590/ejosat.823340

Öz

Veri madenciliği uygulamaları ve iş zekası sistemleri verileri anlamlandırarak bilgiye dönüştürülmesinde ve kuruluşlara karar verme süreçlerinde yardımcı olmak için kullanılır. Çalışmada bir devlet kurumunun personel verileri üzerinde iş zekası ve veri madenciliği süreçleri gerçekleştirilerek verilerin yönetimini sağlamak ve dinamik analizler ile stratejik öngörülerin yapılabilmesi amaçlanmıştır. İş zekası süreçlerinin uygulanmasında Microsoft iş zekası araçlarından SSIS (SQL Server Integration Service), SSAS (SQL Server Analysis Service) ve Power BI kullanılmıştır. Öncelikle veri yapısı modellendirilmiş olup ETL (Extract-Transform-Load) sürecinden geçirilerek anlamlı hale getirilen veri, veri ambarına SSIS programı ile aktarılmıştır. Daha sonra SSAS programı ile OLAP veri küpü oluşturulmuştur. Son olarak da OLAP küpü veri kaynağı olarak belirlenip zengin görsel araçlara sahip olan ve veri analizini çok daha etkili hale getiren Power BI iş zekası aracı kullanılarak çeşitli görsellerle veri analizi gerçekleştirilmiştir. Böylece, karar vericilerin veri analizini etkin bir şekilde yapabilecekleri bir karar destek sistemi geliştirilmiştir. Çalışmada kümeleme analizi yöntemlerinden biri olan K-Means algoritması ve birliktelik kurallarından kurallarından Apriori algoritması ile bir devlet kurumundaki İç Kontrol Sistemi anketi verileri kullanılarak personel memnuniyet analizi yapılmıştır. Veri madenciliği aracı olarak ise içerisinde bulundurduğu bir çok algoritma sayesinde verilerden bilgi çıkarımı yapılabilmesine olanak sağlayan ve açık kaynak kodlu bir araç olması sebebi ile WEKA kullanılmıştır. Kümeleme analizi sonucunda oluşan farklı personel grupları detaylı incelenerek bu gruplara nasıl yaklaşılması gerektiği ve nasıl hitap edilmesi gerektiği belirlenmiştir. Her grubun memnuniyet durumunun farklılaşan noktaları belirlenerek, stratejiler ve uygulama faaliyetleri bu grubun ihtiyacına göre planlanmıştır. Apriori algoritması, personelin İç Kontrol Sistemi anket sorularına vermiş olduğu cevaplar arasında anlamlı ilişkileri bulmak, bu ilişkilerden faydalanarak personelin çalıştığı birimden memnuniyetini karşılaştırarak anlamlı sonuçlar elde etmek ve çalışılan birimden memnun olmama nedenlerini keşfetmek için kullanılmıştır. Böylece İç Kontrol Sistemi anketi verilerinden anlamlı ve yararlı bilgiler elde etmek ve bu bilgiler ışığında personel karar destek planlama faaliyetlerinde destek olmak amaçlanmıştır.

Kaynakça

  • Agrawal, R. and Srikant, R. (1994). Fast Algorithms for Mining Association Rules in Large Databases. Proceedings of the 20th International Conference on Very Large Databases (VLDB), pp. 487-499, Santiago.
  • Akpınar, H. (2000). Veri Tabanlarında Bilgi Keşfi ve Veri Madenciliği. İstanbul Üniversitesi İşletme Fakültesi Dergisi, 29(1), 1-22.
  • Al-Radaideh, Q. A. ve Al Nagi, E. (2012). Using Data Mining Techniques to Build a Classification Model for Predicting Employees Performance. International Journal of Advanced Computer Science and Applications, 3(2), 144-150.
  • Chien, C. ve Chen, L. (2008). Data mining to improve personnel selection and enhance human capital: A case study in high-technology industry, Expert Systems with Applications, 34(1), pp. 280–290.
  • Eren, A. (2018). İş zekası sistemlerinin performans ve karar verme üzerine etkileri, Doktora Tezi, Atatürk Üniversitesi Sosyal Bilimler Enstitüsü, pp. 153-164, Erzurum.
  • Gupta, S. K., Nadia, R., Sipahi, E., Teston, S. F. ve Fantaw, A. (2020). Analysis of the Effect of Compensation on Twitter Based on Job Satisfaction on Sustainable Development of Employees Using Data Mining Methods. International Research Association for Talent Development and Excellence, 12(3), 3289-3313.
  • Jung, Y. ve Suh, Y. (2019). Mining the voice of employees: A text mining approach to identifying and analyzing job satisfaction factors from online employee reviews. Decision Support Systems, vol. 123, pp-1-12.
  • Langit, L., Goff, K. S., Mauri, D., Malik, S. ve Welch, J. (2009). Smart Business Intelligence Solutions with Microsoft SQL Server 2008, Microsoft, pp. 5-8, Washington.
  • Lin, Y. H., Tsai, K. M., Shiang, W. J., Kuo, T. C. ve Tsai, C. H. (2009). Research on using ANP to establish a performance assessment model for business intelligence systems. Expert Systems with Applications, 36(2), pp. 4135-4146.
  • MacQueen, J. (1967). Some methods for classification and analysis of multivariate observations. In: Fifth Berkeley Symposium on Mathematics. Statistics and Probability. University of California Press, pp. 281–297.
  • Matei, G. (2010). A collaborative approach of Business Intelligence systems. Journal of Applied Collaborative Systems, 2(2), 91-101.
  • Michael, H. B. (1999). Business Intelligence Value Chain, DM Review.
  • Negash, S. (2004). Business intelligence. Communications of the AIS, 13(1), pp. 177-195.
  • Shen, Y. (2007). A Formal Ontology for Data Mining: Principles, Design and Evolution, Master Thesis, Department of Mathematics and Computer Science, University of Quebec and Trois-Rivieres.
  • Sheybani, F. (2019). Predicting the Individuals’ job satisfaction and determining the factors affecting it using the CHAID Decision Tree Data Mining Algorithm Case Study: the National Opinion Research Center of the United States. European Journal of Engineering Research and Science, 4(3), 6-9.
  • Talukdar, G. (2016). Human Resources Analytics: An Approach Towards Business Intelligence. International Journal of Computer Sciences and Engineering, 4(7), 125-129.
  • Wang, J., Chen, T. J. ve Chiu, S. H. (2005). Literature Review on Data Warehouse Development, IACIS PaciBic 2005 Conference Program, pp. 987-994.
  • Watson, H. J., Goodhue, D. L. ve Wixom, B. H. (2002). The benefits of data warehousing: why some organizations realize exceptional payoffs. Information & Management, 39(6), pp. 491-502.
  • Yadav, S., Jain, A. ve Singh, D. (2018). Early Prediction of Employee Attrition using Data Mining Techniques, 2018 IEEE 8th International Advance Computing Conference (IACC), pp. 349-354.

A Personnel Business Intelligence System and Measuring Personnel Satisfaction with Data Mining

Yıl 2020, Ejosat Özel Sayı 2020 (ISMSIT), 323 - 334, 30.11.2020
https://doi.org/10.31590/ejosat.823340

Öz

Data mining applications and business intelligence systems are used to make sense of data and to help organizations in their decision-making processes. In the study, it is aimed to manage the data by performing business intelligence and data mining processes on the personnel data of a government institution and to make strategic predictions with dynamic analysis. Microsoft business intelligence tools SSIS (SQL Server Integration Service), SSAS (SQL Server Analysis Service) and Power BI have been used in the implementation of business intelligence processes. First of all, the data structure was modeled and the data, which was made meaningful by passing the ETL (Extract-Transform-Load) process, was transferred to the data warehouse with SSIS program. Then, OLAP data cube was created with SSAS program. Finally, data analysis was carried out with various visuals using the Power BI business intelligence tool, which has been identified as the OLAP cube as a data source and has rich visual tools and makes data analysis much more effective. Thus, a decision support system has been developed where decision makers can perform data analysis effectively. In the study, personnel satisfaction analysis was performed using the K-Means algorithm, one of the cluster analysis methods, and the Apriori algorithm, one of the association rules, and the Internal Control System survey data in a government institution. As a data mining tool, WEKA is used because it is an open source tool that allows information extraction from data thanks to many algorithms it contains. The different staff groups formed as a result of the cluster analysis were examined in detail, and how these groups should be approached and addressed was determined. Different points of satisfaction status of each group were determined and strategies and implementation activities were planned according to the needs of this group. The Apriori algorithm has been used to find meaningful relationships between the responses of the personnel to the Internal Control System survey questions, to obtain meaningful results by comparing the satisfaction of the personnel from the unit they work in, and to discover the reasons for their dissatisfaction with the unit they work with. So it is aimed to obtain meaningful and useful information from the internal control system survey data and to support personnel decision support planning activities in the light of this information.

Kaynakça

  • Agrawal, R. and Srikant, R. (1994). Fast Algorithms for Mining Association Rules in Large Databases. Proceedings of the 20th International Conference on Very Large Databases (VLDB), pp. 487-499, Santiago.
  • Akpınar, H. (2000). Veri Tabanlarında Bilgi Keşfi ve Veri Madenciliği. İstanbul Üniversitesi İşletme Fakültesi Dergisi, 29(1), 1-22.
  • Al-Radaideh, Q. A. ve Al Nagi, E. (2012). Using Data Mining Techniques to Build a Classification Model for Predicting Employees Performance. International Journal of Advanced Computer Science and Applications, 3(2), 144-150.
  • Chien, C. ve Chen, L. (2008). Data mining to improve personnel selection and enhance human capital: A case study in high-technology industry, Expert Systems with Applications, 34(1), pp. 280–290.
  • Eren, A. (2018). İş zekası sistemlerinin performans ve karar verme üzerine etkileri, Doktora Tezi, Atatürk Üniversitesi Sosyal Bilimler Enstitüsü, pp. 153-164, Erzurum.
  • Gupta, S. K., Nadia, R., Sipahi, E., Teston, S. F. ve Fantaw, A. (2020). Analysis of the Effect of Compensation on Twitter Based on Job Satisfaction on Sustainable Development of Employees Using Data Mining Methods. International Research Association for Talent Development and Excellence, 12(3), 3289-3313.
  • Jung, Y. ve Suh, Y. (2019). Mining the voice of employees: A text mining approach to identifying and analyzing job satisfaction factors from online employee reviews. Decision Support Systems, vol. 123, pp-1-12.
  • Langit, L., Goff, K. S., Mauri, D., Malik, S. ve Welch, J. (2009). Smart Business Intelligence Solutions with Microsoft SQL Server 2008, Microsoft, pp. 5-8, Washington.
  • Lin, Y. H., Tsai, K. M., Shiang, W. J., Kuo, T. C. ve Tsai, C. H. (2009). Research on using ANP to establish a performance assessment model for business intelligence systems. Expert Systems with Applications, 36(2), pp. 4135-4146.
  • MacQueen, J. (1967). Some methods for classification and analysis of multivariate observations. In: Fifth Berkeley Symposium on Mathematics. Statistics and Probability. University of California Press, pp. 281–297.
  • Matei, G. (2010). A collaborative approach of Business Intelligence systems. Journal of Applied Collaborative Systems, 2(2), 91-101.
  • Michael, H. B. (1999). Business Intelligence Value Chain, DM Review.
  • Negash, S. (2004). Business intelligence. Communications of the AIS, 13(1), pp. 177-195.
  • Shen, Y. (2007). A Formal Ontology for Data Mining: Principles, Design and Evolution, Master Thesis, Department of Mathematics and Computer Science, University of Quebec and Trois-Rivieres.
  • Sheybani, F. (2019). Predicting the Individuals’ job satisfaction and determining the factors affecting it using the CHAID Decision Tree Data Mining Algorithm Case Study: the National Opinion Research Center of the United States. European Journal of Engineering Research and Science, 4(3), 6-9.
  • Talukdar, G. (2016). Human Resources Analytics: An Approach Towards Business Intelligence. International Journal of Computer Sciences and Engineering, 4(7), 125-129.
  • Wang, J., Chen, T. J. ve Chiu, S. H. (2005). Literature Review on Data Warehouse Development, IACIS PaciBic 2005 Conference Program, pp. 987-994.
  • Watson, H. J., Goodhue, D. L. ve Wixom, B. H. (2002). The benefits of data warehousing: why some organizations realize exceptional payoffs. Information & Management, 39(6), pp. 491-502.
  • Yadav, S., Jain, A. ve Singh, D. (2018). Early Prediction of Employee Attrition using Data Mining Techniques, 2018 IEEE 8th International Advance Computing Conference (IACC), pp. 349-354.
Toplam 19 adet kaynakça vardır.

Ayrıntılar

Birincil Dil Türkçe
Konular Mühendislik
Bölüm Makaleler
Yazarlar

Gizem Çetin 0000-0003-0486-8758

Ömer Özgür Tanrıöver 0000-0003-0833-3494

Yayımlanma Tarihi 30 Kasım 2020
Yayımlandığı Sayı Yıl 2020 Ejosat Özel Sayı 2020 (ISMSIT)

Kaynak Göster

APA Çetin, G., & Tanrıöver, Ö. Ö. (2020). Personel İş Zekası Sistemi ve Veri Madenciliği ile Personel Memnuniyetinin Ölçülmesi. Avrupa Bilim Ve Teknoloji Dergisi323-334. https://doi.org/10.31590/ejosat.823340