International Journal of Neutrosophic Science IJNS 2690-6805 2692-6148 10.54216/IJNS https://www.americaspg.com/journals/show/3898 2020 2020 Department of Banking and Finance, Faculty of Business, Applied Science Private University, Amman, 11937, Jordan Jamil Jamil Department of Finance and Banking, Faculty of Economics, University of Benghazi, Benghazi 1308, Libya Asma S. Alzwi Department of Accounting, Faculty of Economics and Administrative Sciences, the Hashemite University, Zarqa, Jordan Abdullah A. K. Alkhawaldeh Group Life Insurance Department, Euro Arab Insurance Group, Amman, Jordan Sami Nasser Mohammad Alhjahja Business Department, School of business, The University of Jordan, Aqaba, 11937, Jordan Yasar Shatnawi This study evaluates the influence of technology risks on insurance company performance through Insurtech innovation, focusing on the roles of Data Privacy (DP), Skill Gaps (SG), and Financial Risks (FR) in predicting Insurance Performance (IP). Employing a questionnaire survey approach, the research extended historical empirical studies, capturing demographic profiles and study variables measured on a 5-point Likert scale. A pilot study refined the questionnaire, achieving an 80% response rate, and minor adjustments were made to enhance clarity. The dataset included 243 responses from employees of Jordanian insurance companies, with 37 excluded due to incomplete data. Validity and reliability were assessed using Average Variance Extracted (AVE), Composite Reliability (CR), and Cronbach's Alpha, confirming the robustness of the measurement model. Multicollinearity was tested using correlation, Tolerance, and Variance Inflation Factor (VIF), with no significant issues detected. ANOVA tests were conducted to examine the impact of experience and technology level on DP, SG, FR, and IP, revealing significant differences across groups. A multiple regression model demonstrated that DP and FR positively affect IP, while SG has a negative effect. To further predict IP, the dataset was split into 80-20% and 60-40% training-test sets, and a Multilayer Perceptron (MLP) model was employed. The MLP neural network model, using the Rprop method, highlights the importance of DP, SG, and FR in predicting IP, achieving an accuracy of up to 72%. These findings highlight the importance of addressing technology risks and leveraging Insurtech innovations to enhance insurance company performance, providing valuable insights for industry stakeholders and policymakers. 2025 2025 94 112 10.54216/IJNS.260410 https://www.americaspg.com/articleinfo/21/show/3898