This item is available under a Creative Commons License for non-commercial use only
In the recent years, thanks to social media platform, a plethora of information has been available to financial investors, that were traditionally dependent from financial institutions advisors. Strategies are now shared among web users, performances of stocks are commented in web communities and hints and suggestions are travelling on the internet with a fast pace, in a way that was unthinkable few years before. Several attempts have been made in the recent past, to predict Market movements and trends from activity of Financial Social Networks participants, and to evaluate if contributions from individuals with high level of expertise distinguish themselves from the rest of crowd. The Present Work is leveraging 6 years of tweets extracted from the financial platform StockTwits.com, deep diving in its content, and proposing a predictive Neural Network algorithm of Multi-Layer Perceptron type, based on features derived from text, social network and sentiment analysis. Users have been classified based on the performance achieved during the training, consistence of their prediction has been verified throughout the time and, finally, a trading strategy has been proposed based on following the top actors. The outcomes highlighted that expert investors are outperforming the wisdom of the crowd, and the trading schema put together generated a return of 38.6%, in 2015, when S&P500 had a slightly negative balance.
Del Buono, P. (2018) Identifying Expert Investors on Financial Microblog via Artificial Neural Networks, Dissertation M.Sc. in Computing (Data Analytics), DIT, 2018.