<![CDATA[High stock volatility demands responsive prediction for risk mitigation. Traditional indicators like Simple Moving Average (SMA) suffer from lagging effects due to equal data weighting, while complex machine learning models often cause overfitting and lack interpretability, constituting a notable research gap. This study addresses these limitations by implementing the Exponential Moving Average (EMA) method with a dual-period configuration (EMA-10 and EMA-20). The EMA is justified by its recursive exponential smoothing that weights recent prices heavily, maximizing sensitivity to abrupt reversals without excessive noise. Utilizing daily closing prices of PT Bank Negara Indonesia (Persero) Tbk (BBNI) from 2020 to 2025, a desktop automated analytical system was developed using Python and PyQt5. Out-of-sample evaluation yields highly stable performance, with Mean Absolute Percentage Errors (MAPE) of 2.45% for EMA-10 and 3.10% for EMA-20, alongside a 92.86% Directional Accuracy. These key findings confirm the precision of the EMA framework in generating Golden Cross and Death Cross signals during trending market phases, although supplementary momentum filters are needed during sideways consolidation. This research provides a robust, objective technical framework that successfully bridges traditional visual analysis and automated investment decision-making.]]>
Copyrights © 2026
