Hello, Login
X

Forgot Password?

Join Us

to start. Not a member? Join Today!
LinkedIn Join us on
Investment Management Information
“Bridging the theory & practice of investment management”
Email
Advanced Search →
  • Home
  • Journal
    • About
    • Subscribe to the Journal
      • Subscriptions
      • Library Subscriptions
    • Harry M. Markowitz Award
    • Submit a Paper
      • Article Guidelines
      • Practitioner’s Guidelines
    • Reprints & Permissions
  • Conferences
    • JOIM Conference Events
    • About
    • Membership
    • Board Members
  • Library Access
  • Contact
  • Help

0 comments / 2024-11-26 / the JOIM / Articles, Special Issues

Training Machines to Trade Stocks

Vol. 22, No. 4, 2024
Dilip B. Madan and King Wang

Machines are trained to trade stocks by developing an investment policy for stock investment in a Markovian context. Importantly, the investment actions impact just the immediate reward and not the state transitions. The policies are designed to maximize a nonlinear expectation of the undiscounted sum of future rewards using the methods of Now Decision Theory. The nonlinear expectations, unlike expectations, are rendered risk sensitive using a distortion of probabilities. The distortions employed need not be concave and display regions of convexity making them volatility desiring at low volatility levels. The technology is illustrated by trading 589 stocks over 15 years using the policy function.

0 comments… add one
Cancel reply

Leave a Comment

Next Article: Fooled by the Black Swan

Previous Article: Hedging Barrier Options Using Reinforcement Learning

JOIM

    Library Access

    Subscribe to the Journal
    Submit a Paper
    Harry M. Markowitz Award
    Editorial Board
    Upcoming Conferences

    Edit Profile

Recent Comments

    JOIM

      About the JOIM
    • Library Access
    • Subscribe to the Journal
    • Submit a Paper
    • Editorial Board
    • Harry M. Markowitz Award
    • Licensing Rights and Advertising
    • Terms and Conditions

    JOIM Conference Series

    • About
    • Upcoming Conferences
    • Membership
    • Board Members
    • Terms & Conditions
    Speaker Reimbursement Policy

    Contact

    Journal Of Investment Management (JOIM)
    3658 Mt. Diablo Blvd., Suite 200
    Lafayette, CA 94549
    www.joim.com

    customerservice @ joim.com
    (925) 299-7800

    Copyright 2019 — Journal Of Investment Management design by SEO Web Designers