BinConv: A Neural Architecture for Ordinal Encoding in Time-Series Forecasting

TL;DR

This paper introduces BinConv, a convolutional neural network architecture utilizing Cumulative Binary Encoding for improved ordinal-aware time-series forecasting, outperforming existing methods in accuracy and efficiency.

Contribution

The paper proposes Cumulative Binary Encoding for ordinal representation and a convolutional architecture, BinConv, to enhance probabilistic forecasting performance and computational efficiency.

Findings

BinConv outperforms baseline models in accuracy on benchmark datasets.

CBE preserves ordinal and magnitude information effectively.

BinConv requires fewer parameters and trains faster than fully connected models.

Abstract

Recent work in time series forecasting has explored reformulating regression as a classification task. By discretizing the continuous target space into bins and predicting over a fixed set of classes, these approaches benefit from more stable training, improved uncertainty modeling, and compatibility with modern deep learning architectures. However, most existing methods rely on one-hot encoding, which ignores the inherent ordinal structure of the target values. As a result, they fail to convey information about the relative distance between predicted and true values during training. In this paper, we address this limitation by applying \textbf{Cumulative Binary Encoding} (CBE), a monotonic binary representation that transforms both model inputs and outputs. CBE implicitly preserves ordinal and magnitude information, allowing models to learn distance aware representations while operating within a classification framework. To leverage CBE effectively, we propose \textbf{BinConv}, a fully convolutional neural network architecture designed for probabilistic forecasting. We demonstrate that standard fully connected layers are not only less computationally efficient than convolutional layers when used with CBE, but also degrade forecasting performance. Our experiments on standard benchmark datasets show that BinConv achieves superior performance compared to widely used baselines in both point and probabilistic forecasting, while requiring fewer parameters and enabling faster training.