About me

I am Daniele Foroni and I am working as Senior Full-Stack Data Scientist at Stats Perform. In particupar, I create predictive model for various football-related analysis, following the end-to-end process of the model, from the data ingestion and feature creation, through the model tuning, to the deployment in production. Among the various technologies, we use standard machine learning, deep neural networks, and the AWS ecosystem.

Previously, I was a Staff Big Data Research Engineer at Huawei MRC - Munichn Research Center in Munich, Germany.

I received my Ph.D. in Computer Science in 2019 from the University of Trento, under the guidance of my advisor Yannis Velegrakis. During that time, I was also a member of the DbTrento research group.

My Ph.D. thesis is titled: “Putting Data Quality in Context - How to generate more accurate analyses” and tackles the problem of data quality issues in the data and how to handle them. The Ph.D. program has been funded by SkilLab - TIM.

I am a data and sport lover, and mixing these two passion is something that has always pushed me. So, in the spare time, I often like to perform some analyses.

I love music and I am also a guitarist.

Research Interests

My research interests include data mining, in particular data quality and profiling, as well as machine learning applications and knowledge discovery. I am focused on data analysis and data exploration, graph mining techniques, and knowledge extraction from structured and unstructured sources.

Currently, my work is centered on traffic simulations. Traffic mining is an extremely broad area that has not yet been fully investigated. The challenges goes from adapting a single traffic light with the information of the vehicles that are passing on it to combine their data to adapt their behavior accordingly. Such processes are not straightforward and need further investigation, since the complexity of the paths that any vehicle can follow is massive.