The Role of Big Data Analytics in Predicting Financial and Investment Risks

Abstract

The objective of this study was to investigate the effectiveness of big data analytics and machine learning techniques in predicting financial and investment risks by integrating large-scale financial, behavioral, and market datasets from investors in Tehran. This study employed a quantitative, applied, and predictive-correlational research design using large-scale financial and behavioral datasets collected from 420 active investors in Tehran during the 2024–2025 period. Data sources included structured financial transaction records, investment portfolios, market volatility indicators, and behavioral risk measures, as well as sentiment-related financial signals extracted from digital financial environments. Data preprocessing and feature engineering were performed to optimize predictive performance. Multiple machine learning algorithms, including Gradient Boosting, Random Forest, Artificial Neural Network, and Support Vector Machine, were used to develop predictive models. Model performance was evaluated using accuracy, precision, recall, F1-score, and AUC metrics. Correlation analysis and feature importance analysis were also conducted to identify the most influential predictors of financial risk. The results indicated that machine learning models demonstrated high predictive accuracy in financial risk prediction, with the Gradient Boosting model achieving the highest performance (accuracy = 93.14%, AUC = 0.96), followed by Artificial Neural Network and Random Forest models. Behavioral risk indicators showed the strongest predictive influence on financial risk (r = 0.71, p < 0.01), followed by investment volatility exposure (r = 0.64, p < 0.01), risk tolerance (r = 0.58, p < 0.01), and market sentiment (r = 0.46, p < 0.01). Feature importance analysis confirmed that behavioral and volatility-related variables were the most significant predictors of financial risk. These findings demonstrate that big data–driven machine learning models significantly enhance financial risk prediction accuracy compared to traditional approaches. The findings confirm that big data analytics combined with machine learning techniques provides a highly effective and reliable framework for predicting financial and investment risks. The integration of behavioral, financial, and market data enhances predictive accuracy and enables more informed investment decision-making. The results highlight the critical role of big data analytics in improving financial risk management, optimizing investment strategies, and enhancing financial system stability.