Bruno Gonçalves Email & Phone Number

○ Developed and implemented a pipeline to scrape and parse in real time all on-chain activity for the Stacks blockchain.○ Implemented dashboards to track custom metrics of on-chain activity for a variety of DeFi tokens across 10 blockchains.○ Analyzed DEX token swap transactions on Solana and EVM blockchains.○ Analyzed social activity leading up to large scale social movements using geolocated Twitter data.○ Built a fuzzy matching approach to match public and private records based on personal information.○ Edited the book Blockchain Data Science, Springer (Forthcoming, 2025).○ Developed all content for webinars on Advanced NLP, Generative AI, LangChain, HuggingFace, ARIMA and GARCH models,○ Authored blog series on Graphs applied to Data Science, Visualization and a Weekly Newsletter.○ Co-authored the book Charting the Next Pandemic, Springer (2019).

Torino, Piemonte, It

San Francisco, California, Us

New York, Ny, Us

- Large scale analysis of public statements using NLP and sentiment analysis.- Analyzed tens of billions of card transactions using Hive and pySpark- Time series analysis of deposit balances using ARIMA, GARCH and LSTM models.- Causal Inference applied to understanding customer spending behavior- Used Model Based Recursive Partitioning to automatically identify extract relevant customer segments- Performed in depth deposit forecast analyses using both top-down (portfolio level) and bottoms up (individual facility level) approaches with sklearn

New York, Ny, Us

- Applied sentiment analysis and NLP to establish the existence of Happiness Paradox in online social networks- Combined Google Books and geolocated Twitter JSON data to understand the Americanization of English language- Built a global event detector using Hadoop to process Wikipedia MySQL dumps and realtime Wikipedia page view data (crawled using requests, wget)- Measured semantic change of word embeddings between formal and informal contexts using gensim- Applied PCA and KMeans to empirically determine the boundaries of linguistic dialects- Developed several week long courses on Spatial Data Mining and Analysis http://bit.ly/DataTorino and on Machine Learning http://bit.ly/MLPalma using NumPy and SciPy

- Used timeseries analysis to study the coordination of on/offline social phenomena within specific areas defined by government issued shapefiles- Studied tourist travel between cities using Hadoop to process a large scale geolocated Twitter dataset- Developed a Multiplex (multi-layer) model for the influence of human mobility in social structure- Characterized scientific production using a multigigabyte XML bibliographic database spanning over 100 years- Geolocated free form user locations using Google Maps API and Yahoo! Maps API and NLP for analyzing and modeling human mobility

Boston, Ma, Us

- Used Twitter real time stream to forecast in advance the winner of American Idol- Used Twitter and Wikipedia datasets to analyze how the Global Language Network impacts cultural diffusion

- Established the cognitive limitation of Dunbar’s number in online conversations using Network Science- Developed visualizations of spatial datasets using Google Earth, ArcGIS and Processing that were featured in the coverof PNAS and Physics World- Established a statistical global commuting law using Census data from 30 different countries in 6 continents- Main C++ and Python developer of the Global Epidemic and Mobility Modeler (GLEaM) system http://bit.ly/GLEaMviz- Applied Machine Learning methods (SVM, LSA, AdaBoost, sklearn) to detect automated online political bots- Modeled the online navigation patterns and online traffic generated by real users based on Internet router logs- Implemented a real time data collection system to monitor Twitter by accessing their JSON API using tweepy

Torino, Piemonte, It

Atlanta, Ga, Us

Los Alamos, Nm, Us

Los Alamos, Nm, Us

Doctor Of Philosophy - Phd, Theoretical And Computational Physics

Master Of Science - Ms, Computer Science

M.S., Computational Physics

B.S., Physics