Bilinear Input Normalization for Neural Networks in Financial Forecasting

TL;DR

This paper introduces a novel data-driven normalization method tailored for deep neural networks handling high-frequency financial time-series, improving forecasting accuracy without requiring expert domain knowledge.

Contribution

The paper proposes a bimodal-aware normalization scheme integrated into end-to-end training, specifically designed for financial data's unique characteristics, enhancing neural network performance.

Findings

Significant forecasting improvements over existing normalization methods.

Effective handling of high volatility and non-stationarity in financial data.

Validated on large-scale Nordic and US market datasets.

Abstract

Data normalization is one of the most important preprocessing steps when building a machine learning model, especially when the model of interest is a deep neural network. This is because deep neural network optimized with stochastic gradient descent is sensitive to the input variable range and prone to numerical issues. Different than other types of signals, financial time-series often exhibit unique characteristics such as high volatility, non-stationarity and multi-modality that make them challenging to work with, often requiring expert domain knowledge for devising a suitable processing pipeline. In this paper, we propose a novel data-driven normalization method for deep neural networks that handle high-frequency financial time-series. The proposed normalization scheme, which takes into account the bimodal characteristic of financial multivariate time-series, requires no expert knowledge to preprocess a financial time-series since this step is formulated as part of the end-to-end optimization process. Our experiments, conducted with state-of-the-arts neural networks and high-frequency data from two large-scale limit order books coming from the Nordic and US markets, show significant improvements over other normalization techniques in forecasting future stock price dynamics.