Dissertation
BibTex RIS Cite

MULTI-OBJECTIVE SOFTWARE PROJECT COST ESTIMATION USING RECENT MACHINE LEARNING APPROACHES

Year 2024, Volume: 04 Issue: 01, 1 - 14, 31.07.2024

Abstract

Software projects are gaining strategic importance day by day, even in the daily operations of companies in various sectors. With the increasing need, many companies develop software by creating projects both within their own structure and for the needs of different sectors. Accurately estimating the workforce needed for software projects is crucial to accurately estimating project costs and ensuring timely completion. Since the 1970s, the field of software effort estimation has been the subject of extensive research in the literature. While non-algorithmic methods such as expert opinion were used in the beginning, as the problems became more complex and technology and hardware features diversified, the need for different solution approaches emerged. To overcome these difficulties, algorithmic methods such as regression and model-based estimation have been developed. In recent years, however, with advances in technology, especially in the last decade, there has been a growing interest in applying Machine Learning-based models and Artificial Intelligence to software cost estimation. The focus of this study is to explore Machine Learning based prediction methods in the context of software projects. The aim is to analyze their effectiveness by investigating how these methods can improve software cost estimation.

References

  • [1] LIU Qin and MINTRAM Robert C. (2005), "Preliminary Data Analysis", Software Quality Journal, Volume 13, pp. 91-115.
  • [2] SONER Taner (2014), Parametrik Tahmin Modellerinin Yazılım Projelerine Uygulanmasına Yönelik Bir Yazı- lım Paketinin Geliştirilmesi (Master’s Thesis), Ankara University Institute of Science, Ankara.
  • [3] RIJWANI Poonam and JAIN Sonal (2016), "Enhanced Software Effort Estimation using Multi Layered Feed Forward Artificial Neural Network Technique", Procedia Computer Science, Volume 89, pp. 307-312.
  • [4] SAYYAD Shirabad and MENZIES Tim (2005), The PROMISE Repository of Software Engineering Databases, School of Information Technology and Engineering University of Ottawa, Canada, http://promise.site.uot- tawa.ca/SERepository, DoA. 05.03.2023.
  • [5] DANASINGH Asir Antony, BALAMURUGAN Suganya and EPIPHANY Jebamalar Leavline (2016), "Lite- rature Review on Feature Selection Methods for High-Dimensional Data", International Journal of Com- puter Applications, Volume 136, No 10, pp. 9-17.
  • [6] DOKEROGLU Tansel, SEVINC Ender, KUCUKYILMAZ Tayfun and COSAR Ahmet (2019), "A survey on new generation metaheuristic algorithms", Computers & Industrial Engineering, Volume 137, pp. 106040, DOI: 10.1016/j.cie.2019.106040. DoA. 08.07.2023.
  • [7] ERGUZEL Turker, OZEKES Serhat, TAN Oguz and GULTEKIN Selahattin (2015), "Feature Selection and Classification of Electroencephalographic Signals an Artificial Neural Network and Genetic Algorithm Based Approach", Clinical EEG and Neuroscience, Volume 46, No 4, pp. 321-326.
  • [8] ORESKI Stjepan and ORESKI Goran (2014),"Genetic algorithm-based heuristic for feature selection in credit risk assessment", Expert systems with applications, Volume 41, No 4, pp. 2052-2064.
  • [9] WANG Yanqiu, CHEN Xiaowen, JIANG Wei, LI Li, LI Wei, YANG Lei, LIAO Mingzhi, LIAN Baofeng, LV Yingli, WANG Shiyuan, WANG Shuyuan and LI Xia (2011), "Predicting human microRNA precursors based on an optimized feature subset generated by GA–SVM", Genomics, Volume 98, No 2, pp. 73-78.
  • [10] YANG He, DU Qian and CHEN Genshe (2012), "Particle swarm optimization-based hyperspectral dimensio- nality reduction for urban land cover classification", IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Volume 5, No 2, pp. 544-554.
  • [11] DOKEROGLU Tansel, DENIZ Ayca and KIZILOZ Hakan Ezgi (2022), "A comprehensive survey on recent metaheuristics for feature selection", Neurocomputing, Volume 494, No 14, pp. 269-296.
  • [12] RUIZ Roberto, RIQUELME Jose C. and AGUILAR-RUIZ Jesus S. (2006), "Incremental wrapper-based gene selection from microarray data for cancer classification", Pattern Recognition, Volume 39, No 12, pp. 2383-2392.
  • [13] LIU Huan and YU Lei (2005), "Toward integrating feature selection algorithms for classification and cluste- ring", IEEE Transactions on Knowledge and Data Engineering, Volume 17, No 4, pp. 491-502.

GÜNCEL MAKİNE ÖĞRENME YAKLAŞIMLARINI KULLANARAK YAZILIM PROJESİ MALİYET TAHMİNİ

Year 2024, Volume: 04 Issue: 01, 1 - 14, 31.07.2024

Abstract

Yazılım projeleri, çeşitli sektörlerdeki şirketlerin günlük operasyonlarında dahi günden güne stratejik önem kazanmaktadır. Artan ihtiyaçla birçok şirket gerek kendi bünyesinde, gerekse farklı sektörlerin ihtiyacına yönelik olarak projeler yaratarak yazılımlar geliştirmektedir. Yazılım projeleri için ihtiyaç duyulan işgücünü doğru tahmin etmek, proje maliyetlerini doğru tahmin etmek ve zamanında tamamlanmasını sağlamak için çok önemlidir.
1970'lerden bu yana, yazılım efor tahmini alanı, literatürde kapsamlı araştırmaların konusu olmuştur. Başlangıçta uzman görüşü gibi algoritmik olmayan yöntemler kullanılırken, sorunlar karmaşıklaştıkça, teknoloji ve donanım özellikleri çeşitlendikçe farklı çözüm yaklaşımlarına olan ihtiyaç da ortaya çıkmıştır. Bu zorlukların üstesinden gelmek için regresyon ve model tabanlı tahmin gibi algoritmik yöntemler geliştirilmiştir. Son yıllarda ise, özellikle son on yılda olmak üzere teknolojideki gelişmelerle birlikte, Makine Öğrenimi tabanlı modelleri ve Yapay Zekayı yazılım maliyet tahminine uygulamaya yönelik artan bir ilgi olmuştur.
Bu çalışmanın odak noktası, yazılım projeleri bağlamında Makine Öğrenimi tabanlı tahmin yöntemlerini keşfetmektir. Amaç, bu yöntemlerin yazılım maliyet tahminini nasıl iyileştirebileceğini araştırarak, etkinliklerini analiz etmektir.

Supporting Institution

ÇANKAYA ÜNİVERSİTESİ

References

  • [1] LIU Qin and MINTRAM Robert C. (2005), "Preliminary Data Analysis", Software Quality Journal, Volume 13, pp. 91-115.
  • [2] SONER Taner (2014), Parametrik Tahmin Modellerinin Yazılım Projelerine Uygulanmasına Yönelik Bir Yazı- lım Paketinin Geliştirilmesi (Master’s Thesis), Ankara University Institute of Science, Ankara.
  • [3] RIJWANI Poonam and JAIN Sonal (2016), "Enhanced Software Effort Estimation using Multi Layered Feed Forward Artificial Neural Network Technique", Procedia Computer Science, Volume 89, pp. 307-312.
  • [4] SAYYAD Shirabad and MENZIES Tim (2005), The PROMISE Repository of Software Engineering Databases, School of Information Technology and Engineering University of Ottawa, Canada, http://promise.site.uot- tawa.ca/SERepository, DoA. 05.03.2023.
  • [5] DANASINGH Asir Antony, BALAMURUGAN Suganya and EPIPHANY Jebamalar Leavline (2016), "Lite- rature Review on Feature Selection Methods for High-Dimensional Data", International Journal of Com- puter Applications, Volume 136, No 10, pp. 9-17.
  • [6] DOKEROGLU Tansel, SEVINC Ender, KUCUKYILMAZ Tayfun and COSAR Ahmet (2019), "A survey on new generation metaheuristic algorithms", Computers & Industrial Engineering, Volume 137, pp. 106040, DOI: 10.1016/j.cie.2019.106040. DoA. 08.07.2023.
  • [7] ERGUZEL Turker, OZEKES Serhat, TAN Oguz and GULTEKIN Selahattin (2015), "Feature Selection and Classification of Electroencephalographic Signals an Artificial Neural Network and Genetic Algorithm Based Approach", Clinical EEG and Neuroscience, Volume 46, No 4, pp. 321-326.
  • [8] ORESKI Stjepan and ORESKI Goran (2014),"Genetic algorithm-based heuristic for feature selection in credit risk assessment", Expert systems with applications, Volume 41, No 4, pp. 2052-2064.
  • [9] WANG Yanqiu, CHEN Xiaowen, JIANG Wei, LI Li, LI Wei, YANG Lei, LIAO Mingzhi, LIAN Baofeng, LV Yingli, WANG Shiyuan, WANG Shuyuan and LI Xia (2011), "Predicting human microRNA precursors based on an optimized feature subset generated by GA–SVM", Genomics, Volume 98, No 2, pp. 73-78.
  • [10] YANG He, DU Qian and CHEN Genshe (2012), "Particle swarm optimization-based hyperspectral dimensio- nality reduction for urban land cover classification", IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Volume 5, No 2, pp. 544-554.
  • [11] DOKEROGLU Tansel, DENIZ Ayca and KIZILOZ Hakan Ezgi (2022), "A comprehensive survey on recent metaheuristics for feature selection", Neurocomputing, Volume 494, No 14, pp. 269-296.
  • [12] RUIZ Roberto, RIQUELME Jose C. and AGUILAR-RUIZ Jesus S. (2006), "Incremental wrapper-based gene selection from microarray data for cancer classification", Pattern Recognition, Volume 39, No 12, pp. 2383-2392.
  • [13] LIU Huan and YU Lei (2005), "Toward integrating feature selection algorithms for classification and cluste- ring", IEEE Transactions on Knowledge and Data Engineering, Volume 17, No 4, pp. 491-502.
There are 13 citations in total.

Details

Primary Language English
Subjects Computer Software, Software Engineering (Other)
Journal Section Research Article
Authors

Doğay Derya 0009-0006-1680-0530

Osman Berkcan Derya 0009-0000-8541-8446

Tansel Dökeroğlu 0000-0003-1665-5928

Publication Date July 31, 2024
Published in Issue Year 2024 Volume: 04 Issue: 01

Cite

IEEE D. Derya, O. B. Derya, and T. Dökeroğlu, “MULTI-OBJECTIVE SOFTWARE PROJECT COST ESTIMATION USING RECENT MACHINE LEARNING APPROACHES”, Researcher, vol. 04, no. 01, pp. 1–14, 2024, doi: 10.55185/researcher.1350323.

The journal "Researcher: Social Sciences Studies" (RSSS), which started its publication life in 2013, continues its activities under the name of "Researcher" as of August 2020, under Ankara Bilim University.
It is an internationally indexed, nationally refereed, scientific and electronic journal that publishes original research articles aiming to contribute to the fields of Engineering and Science in 2021 and beyond.
The journal is published twice a year, except for special issues.
Candidate articles submitted for publication in the journal can be written in Turkish and English. Articles submitted to the journal must not have been previously published in another journal or sent to another journal for publication.