High inflation significantly affects asset prices, risk premiums, and investor behaviour, making traditional portfolio optimisation models less effective. This study explores the application of artificial intelligence (AI) techniques—specifically machine learning (ML) models and heuristic optimisation algorithms—to enhance portfolio performance during periods of high inflation. Using historical macroeconomic and financial market data, the project trains models to identify inflation-sensitive assets, predict returns, and construct optimal asset allocations. Methods such as Random Forest regression, LSTM neural networks, and Genetic Algorithms are compared with classical approaches like Modern Portfolio Theory (MPT). Performance is evaluated using metrics including Sharpe ratio, risk-adjusted returns, and inflation-adjusted returns. The findings aim to determine whether AI-driven strategies can outperform traditional models when inflation is elevated. This project contributes to the growing domain of AI-based financial modelling and offers practical insights for investors seeking resilience against inflationary volatility. In addition to evaluating performance during inflationary spikes, the study examines how AI models respond to shifting macroeconomic signals such as interest rate hikes, currency fluctuations, and commodity price volatility. By incorporating these variables into the learning framework, the models aim to provide more stable predictions and adaptive asset allocation decisions. This helps assess whether AI can truly capture inflation-driven market distortions better than conventional statistical models, which often assume linear relationships and stable correlations. Furthermore, the project highlights the practical implications of AI-driven optimisation for investors, financial planners, and policymakers operating in inflation-sensitive economies. By demonstrating how machine learning outputs can be integrated into investment decision-making, the study contributes to the growing domain of predictive financial analytics. The broader goal is to understand whether AI can create more resilient and inflation-hedged portfolios in real-world scenarios. The findings are expected to offer valuable insights into designing future-ready investment strategies that remain robust even during prolonged periods of macroeconomic uncertainty.