Task-Based Learning via Task-Oriented Prediction Network with Applications in Finance

TL;DR

This paper introduces TOPNet, a novel end-to-end learning framework that incorporates non-differentiable, task-specific evaluation criteria into model training, demonstrated to improve financial prediction tasks.

Contribution

The paper presents TOPNet, a learnable surrogate loss method enabling direct optimization of non-differentiable, task-specific evaluation metrics in end-to-end models.

Findings

TOPNet outperforms traditional models with standard losses.

TOPNet surpasses models with handcrafted surrogate losses.

Effective in financial prediction tasks like revenue surprise forecasting and credit risk modeling.

Abstract

Real-world applications often involve domain-specific and task-based performance objectives that are not captured by the standard machine learning losses, but are critical for decision making. A key challenge for direct integration of more meaningful domain and task-based evaluation criteria into an end-to-end gradient-based training process is the fact that often such performance objectives are not necessarily differentiable and may even require additional decision-making optimization processing. We propose the Task-Oriented Prediction Network (TOPNet), an end-to-end learning scheme that automatically integrates task-based evaluation criteria into the learning process via a learnable surrogate loss function, which directly guides the model towards the task-based goal. A major benefit of the proposed TOPNet learning scheme lies in its capability of automatically integrating non-differentiable evaluation criteria, which makes it particularly suitable for diversified and customized task-based evaluation criteria in real-world tasks. We validate the performance of TOPNet on two real-world financial prediction tasks, revenue surprise forecasting and credit risk modeling. The experimental results demonstrate that TOPNet significantly outperforms both traditional modeling with standard losses and modeling with hand-crafted heuristic differentiable surrogate losses.