Archival Data and Blazar Classification: A Study Using MOJAVE and Fermi/LAT Sources.

This study uses a web-scraper to pull archival data from the NASA Extragalactic Database (NED) combined with data available from the MOJAVE and Fermi/Lat websites. Scrapping NED allows us to increase parameter space for a Support Vector Machine that can distinguish between BL Lac Objects and Flat Spectrum Radio Quasars. The sample includes 529 unique sources, 231 from the MOJAVE catalog and 298 from Fermi/LAT. This sample size was based upon a source having photo-metric data at 1.4 GHz, 4.85 GHz, 3.4 micrometers (WISE1) and 0.1-100 GEV data from Fermi/LAT. We found that a 5-fold cross-validation SVM with a training/test split of 70% to 30% was able to classify the sample with 81.7% percent accuracy.