Extracting Predictive Information from Heterogeneous Data Streams using Gaussian Processes
This addresses financial market prediction for traders/analysts by providing a framework to handle noisy data, though it is incremental as it applies an existing method to new financial data.
The paper tackled forecasting financial time series by fusing four heterogeneous data domains using online Gaussian Processes with ARD kernels, showing performance gains measured by NRMSE, MAD, and Pearson correlation while identifying options data as particularly valuable.
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.