2017/05/27 by Guy Uziel, Uziel, Guy, Ran El‐Yaniv +2
Computer Science · Decision Sciences · Economics, Econometrics and Finance · Engineering · #Advanced Bandit Algorithms Research #FOS: Computer and information sciences #FOS: Economics and business #Machine Learning (cs.LG) #Mathematical Finance (q-fin.MF) #Risk and Portfolio Optimization #Smart Grid Energy Management #cs.LG #q-fin.MF
paper · pdf · doi:10.48550/arxiv.1705.09800
arxiv created 2017/05/27 · openalex publication_date 2017/05/27 · arxiv updated 2017/05/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Online portfolio selection research has so far focused mainly on minimizing regret defined in terms of wealth growth. Practical financial decision making, however, is deeply concerned with both wealth and risk. We consider online learning of portfolios of stocks whose prices are governed by arbitrary (unknown) stationary and ergodic processes, where the goal is to maximize wealth while keeping the conditional value at risk (CVaR) below a desired threshold. We characterize the asymptomatically optimal risk-adjusted performance and present an investment strategy whose portfolios are guaranteed to achieve the asymptotic optimal solution while fulfilling the desired risk constraint. We also numerically demonstrate and validate the viability of our method on standard datasets.