ORLANDO, Fla. — Financial firms are increasingly turning to artificial intelligence to improve forecasting, risk modeling and decision-making.
As markets move faster and data becomes more complex, banks, asset managers and fintech companies are looking for tools that can help them test scenarios before real money is at risk. One area drawing more attention is synthetic data, which uses artificial intelligence to generate realistic data that can be used for modeling and testing.
Alex Chen, a data scientist and senior IEEE member, said synthetic data can help financial teams study market behavior when real-world data is limited, sensitive or incomplete.
“For me, the challenge was always more than training a model,” Chen said. “It was about building systems that could actually stand in for reality, even when the real data is scarce or incomplete.”
Financial analytics has become a larger part of how institutions manage risk, reporting and strategy. The financial analytics market is valued at $12.49 billion in 2025 and forecast to reach $21.27 billion by 2030, representing an 11.2% CAGR during this period.
Chen’s early work included research tied to synthetic market order simulation, where generative models were used to create realistic order book data. Those systems can help researchers and financial teams test how models perform under different market conditions without relying only on historical data.
Synthetic data can be useful because financial institutions often face limits on how much real trading or customer data they can use. Privacy rules, security concerns and incomplete records can make it harder to build and test models at scale.
Chen said synthetic data is not meant to replace real-world judgment. Instead, it can give teams more ways to ask what could happen under different conditions.
“Synthetic data is not a shortcut. It’s a catalyst,” Chen said. “It gave us a way to ask ‘what if’ at scale, and that’s what ultimately pushes financial innovation forward.”
For those systems to work well, they need strong data foundations. A model trained on incomplete or biased data can produce results that are misleading, even if the technology appears sophisticated.
Chen has continued working at the intersection of machine learning, analytics and applied financial technology.
He said the value of AI in finance depends on whether it can connect research to real business decisions.
“What excites me most is connecting rigorous research to decisions that matter for businesses and people,” Chen said. “The real prize with AI isn’t just accuracy. It’s impact at scale.”
As financial companies continue investing in predictive modeling and generative AI, synthetic data may become a bigger part of how firms test systems, prepare for uncertainty and improve decision-making.
For financial institutions, the goal is not just to build more advanced models. It is to build models that can be tested, trusted and used when market conditions change.
Click here to download our free news, weather and smart TV apps. And click here to stream Channel 9 Eyewitness News live.
©2026 Cox Media Group
