Extracting Predictive Information from Heterogeneous Data Streams using Gaussian Processes

TL;DR

This paper demonstrates how online Gaussian Processes with ARD kernels can effectively fuse diverse financial data sources, improving prediction accuracy and identifying key features, especially highlighting the importance of options data.

Contribution

It introduces a framework for integrating heterogeneous financial data streams using Gaussian Processes with ARD kernels, emphasizing feature relevance and the value of options data.

Findings

ARD kernels provide meaningful feature rankings.

Fusing multiple data sources improves forecasting accuracy.

Options data significantly enhances predictive performance.

Abstract

Financial markets are notoriously complex environments, presenting vast amounts of noisy, yet potentially informative data. We consider the problem of forecasting financial time series from a wide range of information sources using online Gaussian Processes with Automatic Relevance Determination (ARD) kernels. We measure the performance gain, quantified in terms of Normalised Root Mean Square Error (NRMSE), Median Absolute Deviation (MAD) and Pearson correlation, from fusing each of four separate data domains: time series technicals, sentiment analysis, options market data and broker recommendations. We show evidence that ARD kernels produce meaningful feature rankings that help retain salient inputs and reduce input dimensionality, providing a framework for sifting through financial complexity. We measure the performance gain from fusing each domain's heterogeneous data streams into a single probabilistic model. In particular our findings highlight the critical value of options data in mapping out the curvature of price space and inspire an intuitive, novel direction for research in financial prediction.