KO‘CHMAS MULKNI OMMAVIY BAHOLASHNING INNOVATSION TEXNOLOGIYALARI

Jasur Xushvaqtov

KO‘CHMAS MULKNI OMMAVIY BAHOLASHNING INNOVATSION TEXNOLOGIYALARI

Authors

Jasur Xushvaqtov

Keywords:

ommaviy baholash, ko‘chmas mulk, kadastr qiymati, mashinali o‘qitish (ML), LightGBM, XGBoost, CatBoost, regressiya tahlili, GIS.

Abstract

Ommaviy baholash ko‘chmas mulkning kadastr qiymatini aniqlash va hududlar soliq bazasini shakllantirishda
muhim instrument hisoblanadi. Shu bilan birga, amalda qo‘llanilayotgan davlat kadastr baholash usullari asosan an’anaviy
statistik modellarga tayanadi va zamonaviy axborot texnologiyalari taqdim etayotgan imkoniyatlardan yetarli darajada
foydalanmaydi. Mazkur tadqiqotda GIS-texnologiyalar hamda sun’iy intellekt asosida urbanizatsiyalashgan hududlarda
ko‘chmas mulkni ommaviy baholashning zamonaviy yondashuvlari tahlil qilingan.
Tadqiqot jarayonida Toshkent shahri ko‘chmas mulk bozoridan veb-skreyping usuli orqali yig‘ilgan 7 000 ta obyekt
ma’lumotlari asosida mashinali o‘qitish (ML) algoritmlari — LightGBM (Light Gradient Boosting Machine), XGBoost
(eXtreme Gradient Boosting) va CatBoost modellari sinovdan o‘tkazilgan. Natijalar shuni ko‘rsatdiki, an’anaviy chiziqli
regressiya modellari bilan solishtirganda, ML modellari yuqori aniqlikni ta’minlaydi. Xususan, barcha ansambl modellar
uchun determinatsiya koeffitsiyenti (R²) 0,865 ni, o‘rtacha mutlaq foiz xatosi (MAPE) esa 13,5% ni tashkil etdi. Tadqiqot
natijasida mazkur texnologiyalarni davlat kadastr tizimiga integratsiya qilish bo‘yicha ilmiy-amaliy tavsiyalar ishlab chiqildi

Author Biography

Jasur Xushvaqtov

Termiz davlat universiteti mustaqil izlanuvchisi

References

1. D. Wang, V. J. Li. Mass Appraisal Models of Real Estate in the 21st Century: A Systematic Literature Review //

Sustainability. – 2019. – Vol. 11, No. 24. – P. 1–14

2. G. Zhou, Y. Ji, X. Chen, F. Zhang. Artificial Neural Networks and the Mass Appraisal of Real Estate // International

Journal of Online Engineering. – 2018. – Vol. 14, No. 3. – P. 180–187.

3. S. Yalpir, S. S. Durduran, F. B. Unel, M. Yolcu. Creating a valuation map in GIS through artificial neural network

methodology: A case study // Acta Montanistica Slovaca. – 2014. – Vol. 19, No. 2. – P. 79–89.

4. G. Droj, L. Droj. GIS-based automated valuation models – a genuine solution for real estate valuation in Romania //

RevCAD. – 2016. – No. 20. – P. 45–52.

5. M. O. Mete, T. Yomralioglu. Mass Valuation of Real Estate Using GIS-based Nominal Valuation and Machine Learning

Methods // European Real Estate Society (ERES). – 2022. – Paper No. 2022_177. – P. 1–7.

6. S. Sisman, A. C. Aydinoglu. A modelling approach with geographically weighted regression methods for determining

geographic variation and influencing factors in housing price: A case in Istanbul // Land Use Policy. – 2022. – Vol. 119.

– 106183.

7. D. Demetriou. Automating the land valuation process carried out in land consolidation schemes // Land Use Policy. –

2018. – Vol. 75. – P. 21–32.

8. A. El Jaouhari, A. Samadhiya, A. Kumar, A. Šešplaukis, S. Raslanas. Mapping the landscape: A systematic literature

review on automated valuation models and strategic applications in real estate // International Journal of Strategic

Property Management. – 2024. – Vol. 28, No. 5. – P. 286–301.

9. S. Canaz Sevgen, Y. Tanrivermiş. Comparison of machine learning algorithms for mass appraisal of real estate data //

Real Estate Management and Valuation. – 2024. – Vol. 32, No. 2. – P. 15–24.

10. U. T. To‘lakov. Ko‘chmas mulkni soliqqa tortish va ommaviy baholashda ekonometrik modellashtirish // Ilg‘or iqtisodiyot

va pedagogik texnologiyalar. – 2025. – Vol. 2, No. 3. – P. 807–847.

11. X. Sattarov, Sh. Boltabaev, N. Chaudhary, B. Shukla. Analyzing Market Dynamics: An In-Depth Statistical Study of

Real Estate Valuations in Tashkent City’s Residential Sector Using Advanced Data Analytics Techniques // Advanced

Data Analytics in Real Estate. – 2024. – P. 1–18.

KO‘CHMAS MULKNI OMMAVIY BAHOLASHNING INNOVATSION TEXNOLOGIYALARI