| BIO

Mr. Ho Quoc Thang has more than 10 years of experience in Data, Analytics, and AI. At SVTECH, he is responsible for strategic consulting, solution architecture design, and the implementation of enterprise data, advanced analytics, and AI platforms. He has been involved in numerous large-scale projects across banking, consumer finance, insurance, energy, manufacturing, and healthcare.

Combining deep technical expertise with extensive hands-on implementation experience and a strong understanding of business needs, Mr. Thang helps organizations build robust data foundations, unlock the value of data, and scale data-driven capabilities across the enterprise. His consulting focuses on improving operational efficiency, strengthening risk management, enhancing decision-making, and developing practical data and AI transformation roadmaps aligned with each organization’s long-term strategic objectives.

| TOPIC

Data Analytics and Predictive Modeling: Harnessing Big Data for Improved Pricing and Risk Forecasts

| ABSTRACT

The insurance industry is under increasing pressure to deliver faster pricing, greater accuracy, and risk forecasts that more closely reflect real-world market conditions. Yet, while much of the discussion around “big data” remains conceptual, a far more critical question is often overlooked: how should data be structured and governed to ensure that pricing models and risk forecasting can be trusted at operational scale? A predictive model is only as strong as the quality, completeness, and timeliness of the underlying data that supports it.

Drawing on experience in advising enterprises and organizations across the Vietnamese market on data architecture, this presentation focuses on the architectural decisions that truly distinguish insurers capable of leveraging big data for dynamic pricing from those that remain constrained by fragmented and inconsistent data. Together, we will examine how leading organizations have restructured their data foundations by integrating data across multiple business functions and subsidiary companies, embedding data quality governance into the design phase rather than addressing issues retrospectively, and establishing monitoring capabilities to detect model deviations before they affect pricing or claims outcomes.

This is not a product presentation, but rather a discussion for insurance executives and professionals in actuarial, risk management, data, and technology who are seeking practical answers to a fundamental question: how can data be transformed into faster, more accurate, and more responsible pricing decisions? Attendees will gain a practical approach to identifying the right starting point, selecting appropriate use cases, and developing a roadmap for safely, effectively, and scalably embedding predictive analytics into business operations.