This paper presents a novel model for Adaptive Risk Parity Portfolio Construction, designed to dynamically adjust portfolio weights based on changing market conditions and economic regimes. Traditional portfolio strategies, such as Modern Portfolio Theory (MPT), often rely on static assumptions that can lead to suboptimal performance in volatile markets. In contrast, the adaptive risk parity approach aims to equalize risk contributions across asset classes while responding to fluctuations in economic indicators, such as GDP growth and inflation rates. By employing techniques such as Markov switching models and machine learning for regime identification, the proposed model allows for real-time adjustments to asset allocations. The back-testing results demonstrate that the adaptive risk parity portfolio outperforms static risk parity and traditional mean-variance optimized portfolios in terms of risk-adjusted returns and drawdown management. This research contributes to the field of portfolio management by providing a framework that enhances resilience and adaptability in investment strategies.