The first analyzed article is “Predicting the direction of stock market index movement using an optimized artificial neural network model” by Mingyue Qiu and Yu Song. The authors assume that predicting the exact daily price of the stock market demands an accurate and comprehensive analysis of various aspects influencing this factor, such as political stability, the global economy, and traders’ expectations (Qiu & Song, 2016). The use of innovative technologies, such as the optimized artificial neural network model (ANN), can improve the accuracy of the daily stock market index prediction (Qiu & Song, 2016). The authors suggest using genetic algorithms (GA) to improve the effectiveness of the process and verify the investigated phenomenon by integrating a new hybrid GA-ANN model (Qiu & Song, 2016). This method is critical for the sphere as it can help to improve the prediction process.
The leading objective of the study is to improve the prediction accuracy by using the ANN model and test the GA algorithm regarding its capability to offer better results. Comparing their method with the previous studies, they conclude that the hybrid GA-ANN model can be viewed as a potentially advantageous method to increase prediction accuracy and acquire better results (Qiu & Song, 2016). At the same time, the authors state that new upgrades are possible through combining input indicators, using methods different from GA, and specific investment strategies (Qiu & Song, 2016). In such a way, the article outlines how neural networks and AI can alter the sphere of finances.
The article shows that AI can be widely used in the financial sphere. Using artificial networks such as the described one, specialists acquire new tools for forecasting and planning, which is vital for outcomes. The discussed GA-ANN model can help to introduce the positive change in the stock market as the more accurate indexes will add opportunities for decision-making and better financial operations. The article proves that AI is the future of the financial sector as it offers a limitless number of chances to consider numerous factors affecting the current showings and calculate them to avoid mistakes or poor predictions.
The second article is “A novel artificial autonomous system for supporting investment decisions using a Big Five model approach” by Daniel Cabrera-Paniagua and Rolando Rubilar-Torrealba. The authors state that artificial autonomous systems (AAS) are widely used in various spheres to improve decision-making processes and attain better results (Cabrera-Paniagua & Rubilar-Torrealba, 2021). Cabrera-Paniagua and Rubilar-Torrealba (2021) offer the design of the AAS resting on the Big Five model, implying five essential personality profiles, such as openness, conscientiousness, extraversion, agreeableness, and neuroticism. It can be viewed as an innovative approach as existing systems do not support specific decisions regarding the Big Five model (Cabrera-Paniagua & Rubilar-Torrealba, 2021). The paper investigates this framework and its ability to guarantee better results. The central goal is to introduce an AAS for making investment decisions regarding the market conditions and policy function adapting over time (Cabrera-Paniagua & Rubilar-Torrealba, 2021). The latter considers the market conditions and the Big Five model profile (Cabrera-Paniagua & Rubilar-Torrealba, 2021). The study shows that including personality traits in decision-making can lead to enhanced outcomes.
The given research paper is also linked to using AI in the financial sphere. Autonomous systems are becoming an advantageous method to improve the decision-making process because of their ability to consider specific features, such as the Big Five model, and how they might influence the final result. Additionally, by integrating innovative aspects to the already existing models, it is possible to promote better outcomes and ensure that specific strategies employed by specialists working in the sphere will demonstrate higher accuracy of forecasting due to their focus on a higher number of variables.
The third article also revolves around using AI in the financial sector. Lee et al. (2018) introduce the financial network indicators applied to global stock market investment strategies. The researchers try to construct methods for global portfolio management by using AI and specific indicators, which is highly demanded in various practical fields (Lee et al., 2018). Applying the machine learning techniques considering stock price indices, it is possible to acquire a better vision of the current market’s state and increase the accuracy of predictions and effectiveness of various operations (Lee et al., 2018). Such indexes can also be viewed as performance enhancers for regional allocation strategies (Lee et al., 2018). It means that there is much space for additional improvement.
Moreover, the authors emphasize the importance of using machine learning to predict various sphere’s alterations. Using the global stock indices of 10 countries and other showings, it is possible to build a global stock portfolio strategy characterized by the increased accuracy of data and better forecasting (Lee et al., 2018). It means that the study proves the effectiveness of using AI and machine learning techniques in the financial sector as these technologies promote better outcomes and help to minimize mistakes or avoid using false data.
The selected paper also proves AI’s significant role in the modern financial field. Portfolio management is one of the vital tasks specialists face today. Its accuracy influences results and the majority of operations in the sphere. Thus, applying the machine learning techniques, it is possible to increase the accuracy of predictions and ensure the absence of poor data or its misinterpretations. Under these conditions, the fast evolution of AI is critical for the development of the sphere and the emergence of new tools that will be used by specialists to attain existing goals and reduce the number of critical failures.
References
Cabrera-Paniagua, D., & Rubilar-Torrealba, R. (2021). A novel artificial autonomous system for supporting investment decisions using a Big Five model approach.Engineering Applications of Artificial Intelligence, 98, 104107. Web.
Lee, T., Cho, J., Kwon, D., & Sohn, S. (2019). Global stock market investment strategies based on financial network indicators using machine learning techniques.Expert Systems with Applications, 117(1), 228-242. Web.
Qiu, M., & Song, Y. (2016). Predicting the direction of stock market index movement using an optimized artificial neural network model. PLoS ONE, 11(5), e0155133. Web.