{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T07:44:44Z","timestamp":1791963884380,"version":"4.3.4"},"posted":{"date-parts":[[2026]]},"group-title":"SSRN","reference-count":0,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/www.uspto.gov\/ip-policy\/copyright-policy\/copyright-basics"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>We examine a household's optimal consumption and portfolio choice problem over a finite working life subject to unspanned labor income risk. To circumvent the twin mathematical intractabilities of time-dependence and market incompleteness, we introduce a dual-track framework. First, we develop a novel analytical approximation by replacing the deterministic lifecycle with an exponentially distributed random horizon, deriving a rigorous, timehomogeneous benchmark system of coupled integral equations. Second, we engineer a modelbased reinforcement learning (RL) approach. Under state-sensitivity conditions, we prove that for fixed smooth perturbations of a verified interior optimum, one exact Bellman correction yields second-order accuracy in the relative consumption error and portfolio-weight error. Our numerical simulations demonstrate that optimal consumption rates and risky asset allocations decline deterministically as retirement approaches, driven by heightened precautionary motives under compounding income volatility and risk aversion. These structural insights deliver immediate operational value for designing scalable, equitable automated wealth-advising engines.<\/jats:p>","DOI":"10.2139\/ssrn.7606878","type":"posted-content","created":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T06:47:11Z","timestamp":1791960431000},"source":"Crossref","is-referenced-by-count":0,"title":["Finite-Horizon Portfolio Choice with Stochastic Income: From Analytical Approximation to Reinforcement Learning"],"prefix":"10.2139","author":[{"given":"Alain","family":"Bensoussan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeonggyu","family":"Huh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hojin","family":"Ko","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9303-1097","authenticated-orcid":true,"given":"Seyoung","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","container-title":[],"original-title":[],"deposited":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T06:47:11Z","timestamp":1791960431000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ssrn.com\/abstract=7606878"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":0,"URL":"https:\/\/doi.org\/10.2139\/ssrn.7606878","relation":{},"subject":[],"published":{"date-parts":[[2026]]},"subtype":"preprint"}}