Risk-Seeking versus Risk-Avoiding Investments in Noisy Periodic Environments
Abstract
We study the performance of various agent strategies in an artificial investment scenario. Agents are equipped with a budget, , and at each time step invest a particular fraction, , of their budget. The return on investment (RoI), , is characterized by a periodic function with different types and levels of noise. Risk-avoiding agents choose their fraction proportional to the expected positive RoI, while risk-seeking agents always choose a maximum value if they predict the RoI to be positive ("everything on red"). In addition to these different strategies, agents have different capabilities to predict the future , dependent on their internal complexity. Here, we compare 'zero-intelligent' agents using technical analysis (such as moving least squares) with agents using reinforcement learning or genetic algorithms to predict . The performance of agents is measured by their average budget growth after a certain number of time steps. We present results of extensive computer simulations, which show that, for our given artificial environment, (i) the risk-seeking strategy outperforms the risk-avoiding one, and (ii) the genetic algorithm was able to find this optimal strategy itself, and thus outperforms other prediction approaches considered.
Cite
@article{arxiv.0801.4305,
title = {Risk-Seeking versus Risk-Avoiding Investments in Noisy Periodic Environments},
author = {J. Emeterio Navarro Barrientos and Frank E. Walter and Frank Schweitzer},
journal= {arXiv preprint arXiv:0801.4305},
year = {2009}
}
Comments
27 pp. v2 with minor corrections. See http://www.sg.ethz.ch for more info