Russian Federation
UDC 004.891.2
This paper investigates the influence of software development process characteristics on the predictive performance of machine learning models for issue resolution time estimation. The study is based on anonymized open datasets from the Hyperledger, JFrog, and Mojang projects, derived from issue tracking systems used in software development. Random Forest, Gradient Boosting, and CatBoost models were employed for prediction. The results demonstrate a consistent superiority of machine learning approaches over a naive baseline prediction based on the mean value of the target variable. Mean Absolute Error (MAE) was reduced by 37.7–75.5% depending on the dataset, with the best result achieved on the JFrog dataset, where MAE decreased from 14,948 to 3,665 seconds. Feature importance analysis revealed that process-related characteristics provide the greatest contribution to prediction quality, including the number of status changes, the number of participants involved in task execution, and the time to first progress. For the most influential process features, permutation importance values reached 257–540, substantially exceeding the contribution of static task attributes such as issue type and priority. The datasets exhibit varying degrees of process formalization. For the highly structured JFrog records, the coefficient of determination reached 0.76, while for Mojang it did not exceed 0.32. This variability indicates a direct relationship between prediction accuracy and the explanatory power of ML models on the one hand, and the completeness of event logging throughout the task lifecycle in the tracking system on the other. The most significant features and their principal distinctions from other attributes are identified and discussed.
machine learning, issue resolution time prediction, issue tracking systems, Jira, corporate software development, Random Forest, CatBoost, feature importance
1. Shevnina, Yu. S. Metod ocenki sostoyaniya nelineynoy sistemy na osnove logicheskogo analiza dannyh / Yu. S. Shevnina // Izvestiya vysshih uchebnyh zavedeniy. Elektronika. – 2022. – T. 27, № 3. – S. 407-415. – DOIhttps://doi.org/10.24151/1561-5405-2022-27-3-407-415. – EDN BZRDEB.
2. Bevzenko, S. A. Primenenie iskusstvennogo intellekta i mashinnogo obucheniya v razrabotke programmnogo obespecheniya / S. A. Bevzenko // Innovacii i investicii. – 2023. – № 8. – S. 187-191. – EDN ODNEIS.
3. Saltanaeva, E. A. Sravnenie tradicionnyh metodov mashinnogo obucheniya i glubokogo obucheniya / E. A. Saltanaeva, A. A. Shakirov, A. R. Gimaeva // Nauchno-tehnicheskiy vestnik Povolzh'ya. – 2023. – № 12. – S. 379-381. – EDN EQNUHN.
4. Leohin, Yu. L. Metody mashinnogo obucheniya v prikladnyh zadachah prognozirovaniya dinamichno izmenyayuschihsya dannyh / Yu. L. Leohin, S. S. Dymkova, T. D. Fathulin // T-Comm: Telekommunikacii i transport. – 2025. – T. 19, № 8. – S. 49-63. – DOIhttps://doi.org/10.36724/2072-8735-2025-19-8-49-63. – EDN ULVCHG.
5. Gudkov, A. A. Prognozirovanie effektivnosti proektnoy deyatel'nosti na osnove integracii podhodov biznes-analitiki i mashinnogo obucheniya / A. A. Gudkov // Vestnik Volzhskogo universiteta im. V.N. Tatischeva. – 2024. – T. 2, № 1(53). – S. 27-36. – DOIhttps://doi.org/10.51965/2076-7919_2024_2_1_27. – EDN QYXZHC.
6. Chistyakova, K. A. Prakticheskie metody upravleniya realizaciey innovacionnyh proektov na osnove ispol'zovaniya programmnogo obespecheniya “Jira” / K. A. Chistyakova, V. V. Yudin // Nauka i iskusstvo upravleniya / Vestnik Instituta ekonomiki, upravleniya i prava Rossiyskogo gosudarstvennogo gumanitarnogo universiteta. – 2023. – № 1. – S. 80-93. – DOIhttps://doi.org/10.28995/2782-2222-2023-1-80-93. – EDN KXHBSV.
7. Korotkih, A. V. Metody avtomatizirovannoy ocenki trudoemkosti zadach razrabotki programmnogo obespecheniya / A. V. Korotkih, I. V. Potapov // IT. Nauka. kreativ : Materialy I Mezhdunarodnogo foruma: v 5-ti tomah, Omsk, 14–16 maya 2024 goda. – Moskva: Obschestvo s ogranichennoy otvetstvennost'yu "Izdatel'sko-knigotorgovyy centr "Kolos-s", 2024. – S. 213-218. – EDN YPZFCG.
8. Nesterov, Yu. G. Podhod k primeneniyu mashinnogo obucheniya v prognozirovanii zagruzki virtual'nyh vychislitel'nyh sistem / Yu. G. Nesterov, A. P. Kalistratov, G. I. Afanas'ev // Sovremennaya nauka: aktual'nye problemy teorii i praktiki. Seriya: Estestvennye i tehnicheskie nauki. – 2019. – № 11-2. – S. 73-76. – EDN PIIMIH.
9. Telegin, V. A. Ispol'zovanie metodov mashinnogo obucheniya dlya sozdaniya algoritma adaptivnoy ocenki vremeni vypolneniya proektnyh zadach / V. A. Telegin // Innovacionnye nauchnye issledovaniya. – 2023. – № 6-3(30). – S. 146-161. – DOIhttps://doi.org/10.5281/zenodo.8128520. – EDN PXCIGW.
10. Petrun'ko, A. O. Primenenie metodov mashinnogo obucheniya pri upravlenii innovacionnymi proektami / A. O. Petrun'ko, M. F. Ivanov // Estestvenno-gumanitarnye issledovaniya. – 2025. – № 3(59). – S. 909-915. – EDN JUENGB.
11. Sapunov, A. V. Ispol'zovanie cifrovyh tehnologiy v prinyatii upravlencheskih resheniy / A. V. Sapunov, T. A. Sapunova // Vestnik Akademii znaniy. – 2023. – № 1(54). – S. 235-238. – EDN FQOQNR.
12. Li, Y. Identifying self-admitted technical debt in issue tracking systems using machine learning / Y. Li, M. Soliman, P. Avgeriou // Empirical Software Engineering. – 2022. – Vol. 27, No. 6. – P. 1-37. – DOIhttps://doi.org/10.1007/s10664-022-10128-3. – EDN JTDVOO.
13. Van Oosten W., Rasiman R., Dalpiaz F., Hurkmans T. On the effectiveness of automated tracing from model changes to project issues // Information and Software Technology. 2023. Vol. 161. Article 107226. DOI:https://doi.org/10.1016/j.infsof.2023.107226.
14. Montgomery L., Lüders C., Maalej W. An alternative issue tracking dataset of public Jira repositories //Proceedings of the 19th International Conference on Mining Software Repositories. – 2022. – S. 73-77.
15. Lüders C. M., Pietz T., Maalej W. Automated detection of typed links in issue trackers //2022 IEEE 30th International Requirements Engineering Conference (RE). – IEEE, 2022. – S. 26-38.
16. Montgomery L., Lüders C., Maalej W. Mining issue trackers: Concepts and techniques //Handbook on Natural Language Processing for Requirements Engineering. – Cham : Springer Nature Switzerland, 2025. – S. 309-336.
