Implementation of Machine Learning and Data Science in the Process of Making Financial Decisions

The tension that results from people's decisions being affected by external factors is becoming too common. Despite the fact that researchers hope to shed light on stress-coping mechanisms in order to improve decisionmaking processes, it is crucial that they first comprehend the dynamics between the state induced by a stressful environment and the manner in which decisions are made under such conditions. The purpose of this study was to investigate whether or not acute stress affects financial decision-making, with a focus on whether or not stress has a greater impact on positive or negative decisions. When participants were under stress, the reflection effect was more pronounced in their decisions compared to when they were in the no-stress control phase. This indicates that stress affects risk taking, which may amplify irrational tendencies when making decisions. Under disruptive stress, decisionmakers revert to automated reactions to risk, which is consistent with dual-process theories. Preprocessing, feature selection, and model training are all used in the suggested method. Preprocessing makes use of techniques like abbreviation extension and the elimination of numerals and connections. LDA and LR are utilized for feature selection. The proposed model's efficacy is measured with GRU-CNN. The proposed approach is compared with two established approaches, such as GRU and CNN.