Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : International Journal for Applied Information Management

Forecasting AI Model Computational Requirements Using Random Forest and XGBoost with Entity and Domain Characteristics Ayuningtyas, Astika; Wulandari, Rindi Nur
International Journal for Applied Information Management Vol. 4 No. 2 (2024): Regular Issue: July 2024
Publisher : Bright Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/ijaim.v4i2.82

Abstract

This research aims to predict the computational power required by artificial intelligence (AI) models, specifically measured in petaFLOP (Floating Point Operations Per Second), based on their domain and entity characteristics. The study employs Random Forest and XGBoost regression models to predict the amount of computational power needed by AI models. Both models were trained on a dataset that includes features such as the training year, domain (e.g., Language, Vision), and entity characteristics. The results demonstrate that the Random Forest model outperforms XGBoost in terms of prediction accuracy, as indicated by higher R-squared values and lower error metrics. Feature importance analysis revealed that the year of training and domain were the most significant predictors of computational power, with the Language domain emerging as the most influential in both models. The findings highlight the potential for machine learning models to forecast AI computational requirements, which can aid organizations in optimizing computational resources for AI projects. However, the study faces limitations due to data sparsity, particularly in the target variable, and the relatively simple nature of the models employed. Future work should explore incorporating additional features, such as hardware specifications, and leveraging deep learning models to better capture the complexity of AI computational demands. This study lays the groundwork for further research into more precise predictions of AI model resource consumption, helping organizations plan their AI initiatives more effectively.
Co-Authors Abdul Azis Adetya Dyas Saputra Agus Basukesti Agus Basukesti, Agus Ahmad Ashari Ahmad Ashari Akbar, M. Pandu Rizky Ali Mustadi Alif Restu Pramudi Anggraini Kusumaningrum Anggraini Kusumaningrum Anggraini Kusumaningrum Anggraini Kusumaningrum, Anggraini Annurroni, Ilyas Anton Honggowibowo Anton Setiawan Honggowibowo Anton Setiawan Honggowibowo Anton Yudhana Aris Rakhmadi Arwin Datumaya Wahyudi Sumari Cessara, Deno Daseftra Dewi Retnowati, Nurcahyani Dwi Kholistyanto Dwi Nugraheny, Dwi Emy Setyaningsih Fakhri Yahya, Muhammad Ferryka, Putri Zudhah Gabriel Naka Sorateleng Habib Satrio Atmojo Harliyus Agustian Haruno Sajati Heni Pujiastuti Imam Riadi Irawan, Ayu Endita Irawaty, Mardiana Iwan Adhicandra Kholistyanto, Dwi Lely Delvia Sipayung Leonardo Tampubolon Lopes, Jodio Blasius Lukman Nadjamuddin Machsunah, Yayuk Chayatun Machsunah Mauidzhoh, Uyuunul Moh Risaldi Ningsih, Tri Widyastuti Nurcahyani Dewi Retnowati Nurcahyani Dewi Retnowati Nurcahyani Dewi Retnowati Nurcahyani Dewi Retnowati Nurwijayanti Kusumaningrum Nuryatno, Edi Triono Nuryatno, Edy Tri Opsidion Tegar Pratama Pamungkas, Dedi Bintang Pramudi, Alif Restu Pujiastuti, Asih Putra, Novan Ramdanu Retnowati , Nurcahyani Dewi Risaldi, Moh Rochmadi, Tri Rofiq Harun Safiq Rosad Salam Aryanto Sarmini Sipayung, Lely Delvia Sri Winiarti Sucahyo, Nur SUDARYANTO SUDARYANTO Sukmawati, Ellyzabeth Syafriza, Azizatul Alif Syam, Syahriani Tole Sutikno Uyuunul Mauidzhoh Uyuunul Mauidzoh Uyuunul Mauidzoh Wahyusari, Retno Waworuntu, Alexander Wintolo, Hero Wulandari, Rindi Nur Yenni Astuti, Yenni Yuliani Indrianingsih Yuliani Indrianingsih Yuliani Indrianingsih Yuliani Indrianingsih Yuliani Indrianingsih