Published Paper Details:

The rapid evolution of financial technology (Fin-Tech) platforms has revolutionized the financial landscape but has simultaneously introduced significant cybersecurity challenges. Natural Language Processing (NLP)-based security tools have emerged as a promising solution to enhance security measures in these platforms. This study explores the effectiveness of NLP in identifying, mitigating, and preventing cyber threats, such as Fraudulent, Anomaly, and Unauthorized Access. This study explores the efficiency of NLP-based security tools in enhancing the security of fin-tech platforms by leveraging machine learning techniques such as Support Vector Machines (SVM), Random Forest (RF), and K-Nearest Neighbors (KNN). By analyzing patterns in textual data, these tools aim to detect vulnerabilities, predict threats, and mitigate risks in real-time. In this study, researchers used the financial data and textual data. The research evaluates the performance of these ML models, focusing on their accuracy (A_accuracy), precision (P_precision), recall (R_recall), and F1-score (?F1?_score). The experimental result shows that the proposed RF model shows the highest A_accuracy (98.83%), P_precision (97.70%), R_recall (98.64%), and ?F1?_score (98.17%).