MA'LUMOTLARNI INTELLEKTUAL TAHLIL QILISHDA MASHINAVIY O'RGANISH USULLARI
Article Sidebar
Main Article Content
Abstract:
Zamonaviy axborot texnologiyalari rivojlanishi bilan ma'lumotlar hajmi eksponensial sur'atda o'sib bormoqda. Ushbu tadqiqot ishida ma'lumotlar intellektual tahlilida mashinaviy o'rganish usullarining qo'llanilishi va samaradorligi keng qamrovli o'rganildi. Qaror daraxtlari, gradient boosting, neyron tarmoqlar (CNN, LSTM) va transformer asosidagi modellar tahlil qilindi. Eksperimental ishlar davomida Kaggle platformasidan olingan "Customer Churn" va "Stock Price Prediction" ma'lumotlar to'plamlari ustida turli modellarning bashorat va tasniflash samaradorligi sinovdan o'tkazildi. Natijalar shuni ko'rsatdiki, transformer modellari tasniflashda 92% aniqlikka, bashoratda esa 0.033 RMSE ko'rsatkichiga erishdi.
Article Details
How to Cite:
References:
Goodfellow I., Bengio Y., Courville A. Deep Learning. MIT Press, 2016.
Breiman L. Random Forests. Machine Learning, 2001.
Chen T., Guestrin C. XGBoost: A Scalable Tree Boosting System. KDD, 2016.
Vaswani A., et al. Attention Is All You Need. NeurIPS, 2017.
Hochreiter S., Schmidhuber J. Long Short-Term Memory. Neural Computation, 1997.
He K., et al. Deep Residual Learning for Image Recognition. CVPR, 2016.
LeCun Y., Bengio Y., Hinton G. Deep learning. Nature, 2015.