MACHINE LEARNING APPROACHES TO PREDICTIVE RISK ANALYSIS IN
FINANCIAL MARKETS
*Musa Dan-azumi Mohammed1, Ahmad Muhammad Ahmad 2, Mu’utasim Uba Adamu 3,
Mukhtar Shariff Ahmad 4 , Munirah Abdullahi Said 5 and Olasunkanmi Oladiboye 6
1,2,3,4,5
Kano State Institute for Information Technology, Kura, Kano, Nigeria
Corresponding author: musadanzu@[Link]
Abstract:
The increasing complexity and volatility of global financial markets have necessitated advanced
analytical tools for risk management. This study explores the integration of artificial intelligence
and machine learning techniques with financial mathematics to develop predictive models for
market risk analysis. By leveraging time-series data, neural networks, and ensemble learning
methods, the proposed model forecasts risk factors such as value-at-risk (VaR) and expected
shortfall under different market conditions. Comparative analysis with traditional econometric
models shows improved accuracy and adaptability of machine learning-based methods in
capturing non-linear dependencies and sudden shocks in financial data. The research underscores
the importance of AI-driven predictive analytics in modern financial mathematics and its potential
for policy-making and portfolio management.