Big Data-Driven Behavioral Economics: Analysis of Decision Biases in Financial Markets

Abstract

In financial markets, traditional economic theories typically assume that market participants are rational and possess complete information. However, behavioral economics research indicates that investors are often influenced by various psychological biases, leading to irrational decision-making. These biases are particularly evident in financial markets, affecting market efficiency and price discovery mechanisms. With the advancement of big data technologies, analyzing and predicting investor decision-making behavior has become more feasible. By examining large-scale financial data, social media sentiment, and market trading behaviors, common psychological biases in investor decision-making—such as overconfidence, loss aversion, anchoring effects, and herd behavior—can be identified. This study employs big data analytics to explore how these decision biases influence market volatility, asset pricing, and portfolio choices, and further investigates their role in financial markets and their implications for policymakers and investors. The research provides new perspectives for financial market risk management and forecasting, promoting the integration of behavioral finance and big data technologies to enhance market efficiency and stability.