The study found that models that combine data reduced errors by almost 3 per cent, compared to results when only quantitative data are examined.
“An almost 3 per cent improvement doesn’t seem large but it has a significant impact in finance because the new method’s prediction is closer to the real value,” said Professor Mark Johnson, who conducted the study.
“This is of particular interest to traders, brokers and investors who want to make a decision on whether to hold, sell or buy after a certain event.
“For example, Company AAA issues an earnings statement, ASX issues an announcement on the earnings, then the algorithm looks for key words in the announcement and compares these to current quantitative data and predicts the return at the end of next day’s trading.”
Professor Johnson, Zhendong (Tony) Zhao and Nataliya Sokolovska examined the performance of four difference combinations of text and data features, with various weighting schemes to test performance.
The data in the study came from 19,282 announcements from the Australian Securities Exchange over the first half of 2010.
CMCRC found that the best performance in analytics was gained by applying different weights between quantitative and qualitative text data, since it prevented the model reacting to minor fluctuations.
“By analysing the announcement and financial quantitative data the combination of these two different types of data gives the research far more variables to analyse, which seems to have led to more accurate predictions,” Mr Zhao said.
