The financial market is widely recognized as a central indicator of a nation s economic vitality, providing essential credit and liquidity to support investment and capital allocation. It plays a dual role by enabling the growth of corporate capital and enhancing investor wealth. Asset Price Prediction (APP) has been approached through a range of techniques, including Conventional Statistics (CS), Fundamental Analysis (FA), Technical Analysis (TA), Heuristic Rules (HR), and, more recently, Machine Learning (ML). Despite considerable advancements in computational power and algorithmic design, APP remains a complex challenge due to the inherently stochastic and nonlinear behavior of financial markets. Recent state-of-the-art (SOTA) studies report trend prediction accuracy near 79 percent and price prediction accuracy around 27 percent. However, a key limitation of many existing approaches is their inability to provide reliable estimates of predictive uncertainty, which is critical for informed risk management. This work addresses this gap by proposing a Conformal Prediction Ensemble (CPE) framework that incorporates Conformal Prediction (CP) techniques to calibrate the outputs of ML-based APP models. The proposed methodology consists of four sequential steps: ML models generate Close value predictions, which are then calibrated using CP. Next, the Conformal Prediction Intervals (CPIs) are intersected to enhance reliability. Finally, a Random Approach (RA) is used to sample Close values from the resulting intersection set uniformly. Model performance is assessed with and without the application of CP, using the Symmetric Mean Absolute Percentage Error (sMAPE) as the evaluation metric. Empirical validation is carried out on two benchmark indices: the Standard and Poor s 500 (SPX) and the Bovespa Index (IBOV). The CPE framework demonstrates improved predictive robustness by explicitly incorporating uncertainty estimation, thus contributing to a practical and empirically grounded strategy for risk-aware APP in financial markets.