Automatic Domain Adaptation Outperforms Manual Domain Adaptation for Predicting Financial Outcomes
This addresses the challenge of domain adaptation for financial prediction, showing that automated methods can be more effective than expert-driven approaches, though it is incremental in improving existing techniques.
The paper tackled the problem of predicting financial outcomes by comparing manual and automatic domain adaptation of sentiment dictionaries, finding that automatic adaptation outperforms manual methods and achieves state-of-the-art results in predicting excess return and volatility.
In this paper, we automatically create sentiment dictionaries for predicting financial outcomes. We compare three approaches: (I) manual adaptation of the domain-general dictionary H4N, (ii) automatic adaptation of H4N and (iii) a combination consisting of first manual, then automatic adaptation. In our experiments, we demonstrate that the automatically adapted sentiment dictionary outperforms the previous state of the art in predicting the financial outcomes excess return and volatility. In particular, automatic adaptation performs better than manual adaptation. In our analysis, we find that annotation based on an expert's a priori belief about a word's meaning can be incorrect -- annotation should be performed based on the word's contexts in the target domain instead.