Composing Ensembles of Instrument-Model Pairs for Optimizing Profitability in Algorithmic Trading

TL;DR

This paper introduces a two-layer ensemble trading system optimized via grid search, which predicts daily price movements and improves profitability by 20% over standard strategies across various financial instruments.

Contribution

It presents a novel ensemble architecture for short-term market prediction, optimized through grid search, demonstrating significant performance improvements.

Findings

20% profit improvement over benchmark strategies

Effective prediction of daily price directions across multiple instruments

Validated on diverse financial data sets

Abstract

Financial markets are nonlinear with complexity, where different types of assets are traded between buyers and sellers, each having a view to maximize their Return on Investment (ROI). Forecasting market trends is a challenging task since various factors like stock-specific news, company profiles, public sentiments, and global economic conditions influence them. This paper describes a daily price directional predictive system of financial instruments, addressing the difficulty of predicting short-term price movements. This paper will introduce the development of a novel trading system methodology by proposing a two-layer Composing Ensembles architecture, optimized through grid search, to predict whether the price will rise or fall the next day. This strategy was back-tested on a wide range of financial instruments and time frames, demonstrating an improvement of 20% over the benchmark, representing a standard investment strategy.