This work intends to combine technical analysis and the K-means clustering algorithm in portfolio selection. To choose the appropriate number of clusters, this study suggested the Elbow Method and Multi-Criteria Index Model from the most reputable Index, including Silhouette, Calinski-Harabasz, and Davies-Bouldin. We formed the clusters using the annual average risk data for the years 2019 and 2020, and we evaluated the stocks based on the technical analysis used by investors, such as Moving Average Convergence/Divergence (MACD) and Hybrid MACD with Arnaud Legoux Moving Average (ALMA). In the empirical experiment, we used the mean-variance portfolio optimization model to solve the risk minimization issue on a subset of the companies' shares in order to choose the most effective portfolio. The Philippine Stock Market lists 234 and 239 businesses for 2019 and 2020, respectively. All simulations were carried out using the MATLAB environment platform. The COVID-19 condition is significantly riskier than the pre-COVID-19 condition, according to the results. The MACD approach dominates the MACD-ALMA strategy in terms of the number of assets with a positive annual rate of return.