Nuno Oliveira is a Data Scientist at CEiiA in Portugal. His current research is dedicated to the creation of predictive models for the utilization of shared vehicles (e.g., scooters) in diverse geographical areas (e.g., specific geographical areas within Barcelona geofence) and time horizons (e.g., next hour, next day). These models can be important to improve the performance of the sharing services by anticipating the need to reallocate resources (e.g., move vehicles to areas with higher demand) and by providing available vehicles to more users.
Nuno Oliveira finished his PhD in Information Systems and Technologies in 2017. The PhD thesis "Mining Social Media Sentiment to Forecast Stock Market Behavior" analyzes the predictive value of sentiment and attention indicators extracted from social media data for various stock market variables (e.g., returns, volatility, trading volume) of different types of stocks (e.g., indexes, portfolios, aggregate market) by applying a robust methodology (e.g., large datasets, different sentiment sources (e.g., Twitter, StockTwits, surveys), diverse Machine Learning methods, statistical test of predictive accuracy). The most relevant experiments executed during this PhD were published in two journal papers, three conference papers and one book chapter.
His main research interests are: Machine Learning, Deep Learning, Natural Language Processing, Time Series Prediction, Geographical Forecasting, Social Network Analysis, Behavioral Finance