Application of multi-agent games to the prediction of financial time-series

TL;DR

This paper introduces a multi-agent game-based method for predicting future financial time-series movements, which could enhance profit detection and risk management strategies.

Contribution

It presents a novel approach using multi-agent games trained on black-box data for multi-step financial predictions, advancing existing forecasting techniques.

Findings

Potential to identify profit opportunities

Useful for developing improved risk management strategies

Demonstrates the feasibility of multi-agent game predictions

Abstract

We report on a technique based on multi-agent games which has potential use in the prediction of future movements of financial time-series. A third-party game is trained on a black-box time-series, and is then run into the future to extract next-step and multi-step predictions. In addition to the possibility of identifying profit opportunities, the technique may prove useful in the development of improved risk management strategies.