Weak Relation Enforcement for Kinematic-Informed Long-Term Stock Prediction with Artificial Neural Networks

TL;DR

This paper introduces a novel loss function for Kinematic-Informed Neural Networks that weakly enforces velocity relations, improving long-term stock prediction accuracy and robustness against data volatility, outliers, and out-of-distribution challenges.

Contribution

It proposes a new loss function that incorporates velocity relation errors, enhancing the stability and realism of long-term stock predictions in neural network models.

Findings

Statistically significant improvement in prediction accuracy.

Better handling of out-of-distribution data and outliers.

Addresses normalization issues in auto-regressive models.

Abstract

We propose loss function week enforcement of the velocity relations between time-series points in the Kinematic-Informed artificial Neural Networks (KINN) for long-term stock prediction. Problems of the series volatility, Out-of-Distribution (OOD) test data, and outliers in training data are addressed by (Artificial Neural Networks) ANN's learning not only future points prediction but also by learning velocity relations between the points, such a way as avoiding unrealistic spurious predictions. The presented loss function penalizes not only errors between predictions and supervised label data, but also errors between the next point prediction and the previous point plus velocity prediction. The loss function is tested on the multiple popular and exotic AR ANN architectures, and around fifteen years of Dow Jones function demonstrated statistically meaningful improvement across the normalization-sensitive activation functions prone to spurious behaviour in the OOD data conditions. Results show that such architecture addresses the issue of the normalization in the auto-regressive models that break the data topology by weakly enforcing the data neighbourhood proximity (relation) preservation during the ANN transformation.