Sequential optimizing investing strategy with neural networks

TL;DR

This paper introduces a neural network-based investing strategy that leverages game-theoretic probability concepts, using past optimal parameters to make current investment decisions, and demonstrates competitive performance against other methods.

Contribution

It presents a novel neural network investing approach that incorporates game-theoretic ideas and uses previous best parameters for decision-making.

Findings

The proposed strategy performs competitively with other neural network-based strategies.

Using past optimal parameters improves investment decision accuracy.

The method integrates game-theoretic probability with neural networks for finance.

Abstract

In this paper we propose an investing strategy based on neural network models combined with ideas from game-theoretic probability of Shafer and Vovk. Our proposed strategy uses parameter values of a neural network with the best performance until the previous round (trading day) for deciding the investment in the current round. We compare performance of our proposed strategy with various strategies including a strategy based on supervised neural network models and show that our procedure is competitive with other strategies.