Lifetime Portfolio Selection: Using Machine Learning. Irlam, G. abstract bibtex The first half of this paper provides a primer on machine learning and relates it to problems in financial planning. Machine learning proves capable of handling real world complications and details which classical financial planning approaches cannot handle; e.g. taxes, reversion to the mean, and time varying yield curves. The second half of this paper provides a case study of the use of reinforcement learning for making asset allocation, annuitization, and consumption decisions in retirement planning. Machine learning typically delivers within a few percent of the theoretical optimal solution on highly abstract problems. Machine learning is found to outperform other approaches for more complex financial planning problems whose optimal solution is not known. The value of SPIAs and inflationindexed bonds is highlighted by the machine learning approach.
@article{irlam_lifetime_nodate,
title = {Lifetime {Portfolio} {Selection}: {Using} {Machine} {Learning}},
abstract = {The first half of this paper provides a primer on machine learning and relates it to problems in financial planning. Machine learning proves capable of handling real world complications and details which classical financial planning approaches cannot handle; e.g. taxes, reversion to the mean, and time varying yield curves. The second half of this paper provides a case study of the use of reinforcement learning for making asset allocation, annuitization, and consumption decisions in retirement planning. Machine learning typically delivers within a few percent of the theoretical optimal solution on highly abstract problems. Machine learning is found to outperform other approaches for more complex financial planning problems whose optimal solution is not known. The value of SPIAs and inflationindexed bonds is highlighted by the machine learning approach.},
language = {en},
author = {Irlam, Gordon},
keywords = {/unread, ⛔ No DOI found},
pages = {16},
}
Downloads: 0
{"_id":"F2k4BC8pmTtJLNogQ","bibbaseid":"irlam-lifetimeportfolioselectionusingmachinelearning","author_short":["Irlam, G."],"bibdata":{"bibtype":"article","type":"article","title":"Lifetime Portfolio Selection: Using Machine Learning","abstract":"The first half of this paper provides a primer on machine learning and relates it to problems in financial planning. Machine learning proves capable of handling real world complications and details which classical financial planning approaches cannot handle; e.g. taxes, reversion to the mean, and time varying yield curves. The second half of this paper provides a case study of the use of reinforcement learning for making asset allocation, annuitization, and consumption decisions in retirement planning. Machine learning typically delivers within a few percent of the theoretical optimal solution on highly abstract problems. Machine learning is found to outperform other approaches for more complex financial planning problems whose optimal solution is not known. The value of SPIAs and inflationindexed bonds is highlighted by the machine learning approach.","language":"en","author":[{"propositions":[],"lastnames":["Irlam"],"firstnames":["Gordon"],"suffixes":[]}],"keywords":"/unread, ⛔ No DOI found","pages":"16","bibtex":"@article{irlam_lifetime_nodate,\n\ttitle = {Lifetime {Portfolio} {Selection}: {Using} {Machine} {Learning}},\n\tabstract = {The first half of this paper provides a primer on machine learning and relates it to problems in financial planning. Machine learning proves capable of handling real world complications and details which classical financial planning approaches cannot handle; e.g. taxes, reversion to the mean, and time varying yield curves. The second half of this paper provides a case study of the use of reinforcement learning for making asset allocation, annuitization, and consumption decisions in retirement planning. Machine learning typically delivers within a few percent of the theoretical optimal solution on highly abstract problems. Machine learning is found to outperform other approaches for more complex financial planning problems whose optimal solution is not known. The value of SPIAs and inflationindexed bonds is highlighted by the machine learning approach.},\n\tlanguage = {en},\n\tauthor = {Irlam, Gordon},\n\tkeywords = {/unread, ⛔ No DOI found},\n\tpages = {16},\n}\n\n","author_short":["Irlam, G."],"key":"irlam_lifetime_nodate","id":"irlam_lifetime_nodate","bibbaseid":"irlam-lifetimeportfolioselectionusingmachinelearning","role":"author","urls":{},"keyword":["/unread","⛔ No DOI found"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/victorjhu","dataSources":["CmHEoydhafhbkXXt5"],"keywords":["/unread","⛔ no doi found"],"search_terms":["lifetime","portfolio","selection","using","machine","learning","irlam"],"title":"Lifetime Portfolio Selection: Using Machine Learning","year":null}