Complexity Pursuit: Separating Interesting Components from Time Series
Neural Computation
| Hi-index | 0.00 |
We compare pre-processing time series data using Complexity Pursuit (CP) 2 and Logarithm Complexity Pursuit (LCP) [2] with a view to subsequently using a multi-layer perceptron (MLP) to forecast on the data set. Our rationale [1] is that forecasting the underlying factors will be easier than forecasting the original time series which is a combination of these factors. The projections of the data onto the filters found by the pre-processing method were fed into the MLP and it was trained to find Least Mean Square Error (LMSE). Both methods find interesting structure in the time series but LCP is more robust and achieves the best (in terms of least mean square error) performance.