Giuseppe Attanasio
- PhD Student, Department of Control and Computer Engineering, Politecnico di Torino
- giuseppe.attanasio@polito.it
- Founder, Kupata S.r.l.
I’m a second-year Ph.D. student at the Department of Control and Computer Engineering of Polytechnic of Turin. I have a Computer Science background. During my first year, I worked on modeling and forecasting financial time series but I’m slowly drifting to NLP with a particular focus on inspection and regularization of language models.
I currently live in Turin. I love reading (Sci-Fi, please) and playing basketball, while circumstances led me to discover that I’m not so bad at cooking. I also like DIY and automating boring stuff.
Besides that, I am a passionate learner. I spend countless hours on lectures and tutorials about languages, frameworks, and technologies which I deem interesting.
Interests. Sequence modeling and forecasting algorithms, inspection and understanding of deep NLP models, applied ML for quantitative trading
Publications
- Leveraging the explainability of associative classifiers to support quantitative stock trading, Proceedings of the 6th Workshop on Data Science for Macro-modeling with Financial and Economic Datasets. Attanasio G., Cagliero L., Baralis E.
- DSLE: A Smart Platform for Designing Data Science Competitions, Proceedings of 44th IEEE Annual Computers, Software, and Applications Conference. Attanasio G., Giobergia G., Pasini A., Ventura F., Baralis E., Cagliero L., Garza P., Apiletti D., Cerquitelli T., Chiusano S.
-
PoliTeam @ AMI: Improving Sentence Embedding Similarity with Misogyny Lexicons for Automatic Misogyny Identification,
Preprint. Attanasio G., Pastor E. - Leveraging the explainability of associative classifiers to support quantitative stock trading, Proceedings of the Sixth International Workshop on Data Science for Macro-Modeling (DSMM ‘20). Attanasio G., Cagliero L., Baralis E.
- DSLE: A Smart Platform for Designing Data Science Competitions, 2020 IEEE 44th Annual Computers, Software, and Applications Conference (COMPSAC). Attanasio G. et al.
- Training ensembles of faceted classification models for quantitative stock trading, Computing, Springer. Cagliero L., Attanasio G., Garza P., Baralis E.
- Combining news sentiment and technical analysis to predict stock trend reversal, Proceedings of the 9th ICDM Workshop on Sentiment Elicitation from Natural Text for Information Retrieval and Extraction. Cagliero L., Attanasio G., Garza P., Baralis E.
- Quantitative cryptocurrency trading: exploring the use of machine learning techniques, Proceedings of the 5th Workshop on Data Science for Macro-modeling with Financial and Economic Datasets. Attanasio G., Cagliero L., Garza P., Baralis E.
- HOT: Hold your own tools for AR-based constructive art, 2017 IEEE Symposium on 3D User Interfaces (3DUI). Attanasio G., Cannavò A., Cibrario F., Lamberti F., Montuschi P., Paravati G.
Projects
- Metastatic cancer identification on Whole Slide Images The project focused on the identification of metastatic cancer areas in human colonic tissue samples. The task involved the preprocessing and the classification of Whole Slide Images by training established deep convolutional networks models from scratch.
- Prometeo Desktop Prometeo is a Windows desktop application, wrote in C#. It allows its user to exchange files and folders across the LAN in a peer-to-peer architectural model.
- Idia Idia is an Android application, written in Java and Kotlin. It’s main goal is to create and empower a community where people can share their own books.