Can Sentiment Indicators Signal Market Reversals?
33 Pages Posted: 29 May 2016
Date Written: May 27, 2016
Abstract
In this study we use machine learning algorithm to test Amareos sentiment indicator's predictive power of market reversals. We then build and test a viable trading strategy.
As input for the algorithm, we used eight market sentiment indicators (Anger, Anticipation, Disgust, Fear, Gloom, Joy, Optimism and Sentiment) on 20 major equity indices from January 1, 2005 to April 15, 2016.
As the target output, we use a classification of the performance of the indices on the following 182 days - approximately six months - split between bottom, top and neutral days.
Our learning algorithm is of the type called random forest. Through calibration on a training set composed of 64% of the data, we obtain a final set of decision trees, or forest. We then examine the out of sample accuracy of this forest on the remaining 36% of the data.
As the accuracy on the test set is relatively high - a result that cannot be explained just by luck - we simulate a trading strategy based on the forest output. The resulting trading strategy produces strong performance, certainly much better than a simple buy and hold, even when adjusted for risk.
Keywords: Machine Learning, Stock Market, Market Sentiment, Quantitative
JEL Classification: C00, C10, C50, C53, G00, G10, G11
Suggested Citation: Suggested Citation