Artificial Intelligence in Finance: Coffee Commodity Trading Big Data for Informed Decision Making

• Published in: IEEE access Vol. 12; pp. 91780 - 91792
• Main Authors: Le, Ngoc-Bao-van, Seo, Yeong-Seok, Huh, Jun-Ho
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Artificial intelligence; Big Data; Coffee; Coffee big data; coffee commodity trading; Commodities; Contracts; Data analysis; Data collection; Data mining; Data models; Data visualization; data warehouse; Data warehouses; Decision making; Decision support systems; Design parameters; Documentation; ETL process; Financial services; Futures; informed decision-making; Predictive models; Pricing; Stock markets
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2024.3409762

Coffee, the second-largest global soft commodity, can take advantage of a comprehensive mining of daily and historical market data for more effective informed trading decisions. Advanced ICT and data mining technologies can change the trading market operation. The existing systems are confronted with certain constraints, including incomplete data, insufficient documentation for storage, and a requirement for a scalable infrastructure for big data analytics, such as a data warehouse or data lakehouse. To address this issue, the paper presents a design and implementation of a coffee commodity trading big data warehouse capable of analyzing various essential parameters for supporting informed decision-making. First, the designed system can automatically collect coffee trading data for New York Arabica coffee futures prices from selected worldwide reports and financial data portals. Next, the Extract, transform, and load (ETL) process is adopted to ingest coffee futures trading crawled data into the 3 layers data warehouse. Finally, the analytical system will extract and visualize selected key dimensions that influence coffee futures prices within different observation windows and perspectives. As a result, we implement a prototype of a coffee trading data warehouse on the crawled data from January 2000 to October 2022 and visualize trends in coffee futures prices based on the collected data for informed decision-making. The construction system is capable of stably operating and processing large volumes of transaction data. This paper will be valuable documentation for reference and decision support for coffee commodity trading enterprises and contribute to the development of future forecasting algorithms.