Machine learning in weekly movement prediction

TL;DR

This paper introduces a weekly stock movement prediction method using novel features and an objective benchmark, demonstrating robust performance of trained models, especially MLP, across diverse market trends.

Contribution

It proposes predicting weekly stock movements with new features and a novel random trader benchmark, enhancing objectivity and standardization in evaluation.

Findings

MLP shows stability and robustness across diverse data

The benchmark is independent of ML models, providing a standard

Incorporates scaling laws and directional changes as features

Abstract

To predict the future movements of stock markets, numerous studies concentrate on daily data and employ various machine learning (ML) models as benchmarks that often vary and lack standardization across different research works. This paper tries to solve the problem from a fresh standpoint by aiming to predict the weekly movements, and introducing a novel benchmark of random traders. This benchmark is independent of any ML model, thus making it more objective and potentially serving as a commonly recognized standard. During training process, apart from the basic features such as technical indicators, scaling laws and directional changes are introduced as additional features, furthermore, the training datasets are also adjusted by assigning varying weights to different samples, the weighting approach allows the models to emphasize specific samples. On back-testing, several trained models show good performance, with the multi-layer perception (MLP) demonstrating stability and robustness across extensive and comprehensive data that include upward, downward and cyclic trends. The unique perspective of this work that focuses on weekly movements, incorporates new features and creates an objective benchmark, contributes to the existing literature on stock market prediction.