Research Areas

My research interests lie in the field of Data Science for Social Good, Nowcasting, and Forecasting, with the use of Big Data Analytics, Data Mining, and Machine Learning. Using Big Data deriving from everyday life as external proxies, it is possible to nowcast and forecast the evolution of phenomena whose study relies only on historical data or data that come with a significant lag.

Data Science for Social Good

Data Science for Social Good refers to the use of Data Science for positive social impact, in a fair and equitable manner. It focuses on tackling important social, environmental, and public health challenges that exist today, using Big Data and new powerful data-driven tools. Data abundance combined with powerful Data Science techniques has the potential to dramatically improve our lives in many different ways. We can exploit medical data to build models able to help in diagnosing and curing diseases. We can use social data and news data to observe and measure the peacefulness of a nation and the well-being of its people.


Nowcasting is defined as the prediction of the present, the very near future, and the very recent past in economics. The term is a contraction for now and forecasting and has been used for a long-time in meteorology. It has recently become popular in economics as standard measures used to assess the state of an economy, e.g., gross domestic product (GDP), are only determined after a long delay, and are even then subject to subsequent revisions. We are now introducing nowcasting in different phenomena such as Health, Human Behaviour, and Social Indices.


Forecasting is the process of making predictions of the future based on past and present data and most commonly by analysis of trends. A commonplace example might be the estimation of some variable of interest at some specified future date. An important distinction in forecasting, in comparison to nowcasting, is that the future is completely unavailable and must only be estimated from what has already happened. Forecasting has applications in a wide range of fields where estimates of future conditions are useful.

Big Data Analytics – Data Mining – Machine Learning

Big Data Analytics examines large amounts of data to uncover information, such as hidden patterns, and correlations, that can help us make informed decisions. Data Mining is an analytical process designed to explore Big data in search of consistent patterns and/or systematic relationships between variables, and then to validate the findings by applying the detected patterns to new subsets of data. Machine learning methods exploit large training datasets of examples to learn general rules and models to classify data and predict outcomes.