In this work, we consider weighted signed network representations of financial markets derived from raw or denoised correlation matrices, and examine how negative edges can be exploited to reduce portfolio risk. We then propose a discrete optimization scheme that reduces the asset selection problem to a desired size by building a time series of signed networks based on asset returns. To benchmark our approach, we apply two standard allocation rules: Markowitz mean-variance optimization and the 1/N strategy, both on the reduced universe and on the full universe of 21 major S&P500 companies over the 2020–2024 period. Empirical results show that portfolios constructed via our signed network selection perform as good as those from the classical Markowitz model and the equal-weight benchmark in most occasions.