A new scientific research conducted by King Abdulaziz University has revealed innovative techniques and methods to enhance cognitive capabilities within modern technological environments and programs through the use of artificial intelligence. These efforts come in the context of aiming to improve accuracy in predictions, enhance decision-making effectiveness, and optimize resource allocation in intelligent systems.
This scientific research falls under the scope of the College of Computer Science and Information Technology and involved a team consisting of the researcher Nadim Abdullah Malibari and his supervisors, Dr. Iyad Katib and Dr. Rashid Mahmoud. The study shed light on utilizing massive amounts of data generated by smart devices and the Internet of Things, in addition to technological advancements, with the aim of enhancing decision-making processes based on specific data, and improving the intelligence and efficiency of modern systems comprehensively.
This scientific research focused on innovative advancements that involve effective responsiveness to the environment, evaluating complex data, making timely knowledge-based decisions, and identified four essential aspects including digital systems and structures, data and information handling, detection and the Internet of Things with data creation, and mobility. Thus, this research laid a solid foundation for the growth of intelligent systems.
This study contributed to enhancing a deeper understanding of these key components to achieve greater progress in the field of intelligent systems. The study offers a comprehensive and practical approach to improve intelligent systems within the financial information technology sector, providing financial institutions with the necessary tools and methods to maximize the benefits of data analysis-based decision-making processes.
Based on the study findings, institutions can adapt to rapid changes in markets and capitalize on profitable opportunities within the competitive financial environment that is part of the financial technology sector. Additionally, this study contributes to offering an advanced strategy based on artificial intelligence to enhance financial technology applications. This strategy relies on two modern technical patterns, namely “Vision Transformers” and “Transformer-Enhanced Learning”.
The study relied on “Vision Transformers” patterns originally developed for image classification. These patterns are characterized by their “attention mechanism,” allowing them to perceive extended relationships in the data. Consequently, they were used to increase the accuracy of classifying sequential data in technology-dependent financial fields and to make informed predictions.
This is attributed to the exceptional efficiency of “Vision Transformers” in deriving temporal correlations and identifying complex spatial patterns through the analysis of sequential data.
The study revealed that precise data segmentation into small pieces with site-specific encryption contributes to accurate and impactful analysis of financial data. Conversely, transformer-based machine learning excels in representing complex decision-making processes within intelligent systems, integrating the information in the general context and guiding decisions based on historical data and market conditions.
This approach opens the door to developing smart investment plans using financial robots and offering automated investment advice. Automated advice is offered as a service based on precise data analytics and algorithmic applications to provide guidance and recommendations in investment areas such as stocks, bonds, and mutual funds. This advice is based on evaluating personal investor data, defining investment goals and expectations, measuring risk tolerance, deciding on the most suitable investment strategy, as well as monitoring performance and adjusting the strategy as needed.
The study showed that robot-advisory consultations rely on complex mathematical formulas and statistical analyses to achieve outstanding performance and issue accurate recommendations. This is done by developing analytical powers and making informed decisions in the financial field, providing optimized and highly efficient results for traders and investors. The results presented by this study contribute to strengthening the world of financial technology and improving the performance of intelligent systems. These modern methods help increase prediction accuracy, improve decision-making capabilities, and maximize resource distribution efficiency within intelligent systems, ultimately supporting the success of companies and institutions in the volatile and competitive financial technology environment.
