Mapping the Methodological Bifurcation of Quantitative Portfolio Optimization: A PRISMA-Compliant Systematic Review with BERTopic–SPECTER Analysis (2003–2025)

Quantitative portfolio optimization has accelerated sharply since 2018, with deep learning and reinforcement learning agents now competing with the mean-variance framework that defined six decades of research. Existing narrative reviews struggle to track this expansion. We screen 832 documents from Scopus and Web of Science under PRISMA 2020 and retain 589 unique articles spanning 2003–2025. Applying BERTopic with SPECTER scientific embeddings, UMAP and HDBSCAN, we identify five coherent topics with mean coherence 0.864: classical mean-variance (T0; n = 270), deep reinforcement learning (T1; n = 116), machine-learning return forecasting (T2; n = 87), covariance estimation and robust optimization (T3; n = 52) and metaheuristics (T4; n = 56). A rank-weighted similarity analysis, designed to neutralise the c-TF-IDF collinearity artefact, shows that deep reinforcement learning is the most isolated paradigm. The two methodological families bifurcate over time: AI / deep-learning approaches grow from 3.6 % of annual output before 2018 to 40.2 % afterwards, while classical methods retain volume but lose share. We synthesise the empirical practices of each family along five dimensions critical to applied finance and identify three under-explored integration frontiers.