Claim Missing Document
Check
Articles

Found 3 Documents
Search

Decentralized Materials Data Management using Blockchain, Non-Fungible Tokens, and Interplanetary File System in Web3 Warmayana, I Gede Agus Krisna; Yamashita, Yuichiro; Oka, Nobuto
Journal of Applied Data Sciences Vol 6, No 1: JANUARY 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i1.380

Abstract

In materials science, utilizing globally distributed data is essential for advancing materials design through technologies such as materials informatics. Achieving this requires secure, transparent, and efficient methods for managing and sharing materials data. This study explores the potential of blockchain, smart contracts, Non-Fungible Tokens (NFTs), and the InterPlanetary File System (IPFS) within the Web3 framework for managing and sharing materials data. We developed and tested a prototype data management system using a thermophysical properties dataset. This system facilitates NFT minting, data storage on IPFS, and secure, traceable ownership transfer of NFTs, enhancing traceability, transparency, and security in data sharing. Additionally, decentralized systems employing blockchain technology, smart contracts, NFTs, and IPFS effectively address vulnerabilities associated with single points of failure common in traditional centralized systems. This study offers valuable insights for future materials design, demonstrating the efficacy of blockchain and related technologies in managing and sharing materials data.
Predictive Analysis for Optimizing Targeted Marketing Campaigns in Bike-Sharing Systems Using Decision Trees, Random Forests, and Neural Networks Warmayana, I Gede Agus Krisna; Yamashita, Yuichiro; Oka, Nobuta
Journal of Digital Market and Digital Currency Vol. 2 No. 1 (2025): Regular Issue March
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jdmdc.v2i1.29

Abstract

This research explores the use of machine learning models to predict bike rental demand and optimize targeted marketing campaigns in bike-sharing systems. Utilizing the day.csv and hour.csv datasets, which provide daily and hourly bike rental data, we implemented Decision Tree Regressor, Random Forest Regressor, and Neural Networks (MLPRegressor) to forecast demand. The Random Forest model outperformed the others, achieving an RMSE of 709.08 and an MAE of 469.99 for daily predictions, while the Neural Network demonstrated potential for hourly forecasts. Our analysis revealed significant trends, including increased demand during summer months and peak usage times on weekday mornings and evenings, highlighting the importance of temporal and weather-related factors in predicting bike rental demand. The study's predictive insights allow bike-sharing companies to enhance operational efficiency by optimizing bike allocation during peak periods and reducing idle capacity during off-peak times. Furthermore, the ability to predict demand accurately enables the development of data-driven marketing strategies, such as launching promotions during high-demand periods and targeting specific user groups based on rental patterns. Despite the promising results, challenges such as data preprocessing complexities and computational resource constraints were encountered. Additionally, the study's scope was limited by the available data, suggesting the need for future research to incorporate additional data sources, like real-time traffic conditions and social events, and to explore more advanced machine learning techniques to further improve prediction accuracy. In conclusion, this research underscores the value of predictive analytics in optimizing bike-sharing systems and marketing strategies, contributing to more efficient and user-centric urban mobility solutions.
Predicting FIFA Ultimate Team Player Market Prices: A Regression-Based Analysis Using XGBoost Algorithms from FIFA 16-21 Dataset Warmayana, I Gede Agus Krisna; Yamashita, Yuichiro; Oka, Nobuto
International Journal Research on Metaverse Vol. 2 No. 2 (2025): Regular Issue June 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/ijrm.v2i2.25

Abstract

This study investigates the use of XGBoost, a machine learning algorithm, for predicting player prices in FIFA Ultimate Team (FUT) from FIFA 16 to FIFA 21. Virtual economies in gaming, particularly in FUT, have grown substantially, with in-game asset prices influenced by a variety of factors such as player attributes, performance metrics, and market dynamics. The objective of this research is to enhance the accuracy of price predictions in FUT through advanced machine learning techniques. The dataset comprises historical player data, including attributes such as rating, skills, and in-game statistics. XGBoost was employed due to its ability to handle large, complex datasets and capture non-linear relationships effectively. The model achieved an R-squared value of 0.8911, indicating that it explains 89% of the variance in player prices, while the RMSE value of 30368.85 reveals the model's precision in estimating prices. Feature importance analysis showed that attributes such as WorkRate and Rating significantly influenced price predictions. Compared to traditional methods like linear regression, XGBoost provided superior accuracy and computational efficiency, making it a valuable tool for understanding player price dynamics in virtual gaming markets. The findings suggest that accurate price predictions can improve gaming strategies for players and provide valuable insights for game developers in optimizing virtual economies. This research also highlights the potential for further exploration using advanced machine learning algorithms to predict price fluctuations in gaming environments.