Gianmario Spacagna

120 Followers

10 SlideShares 120 Followers 126 Followings

I believe that many real-world problems can be solved in a clean and elegant data-driven fashion. Currently Data Scientist at Pirelli, Milan. Areas of interest: Connected Vehicles and Predictive modelling for Cyber Technologies. Founder and coordinator of the Data Science Milan community (www.datas iencemilan.org) Summary: * Commercial and technical experience of modeling unsupervised and predictive solutions for enterprise problems. * Co-author of the Professional Data Science Manifesto (www.datasciencemanifesto.com). * Distributed data processing using Spark, Hadoop and related technologies. * Scaling Machine learning pipelines. * Functional Programming Developer. * Passionate about ...

machine learning artificial intelligence scalability enterprise big data engineering spark leadership science scala agile financial services alluxio logical datawarehouse data science jdbc hdfs in-memory ai genetic algorithm tunup data mining cloud computing dunn clustering davies bouldin amazon elastic compute cloud cluster aic k-means silhouette adjusted rand hadoop question answering llms genai language models generative algorithms entity recognition recommender systems artificial social intelligence market research panelists latent affinities production systems serverless aws cloud architecture productivity software vademecum team building planning products management strategy product management python h2o auto-encoders anomaly detection tuning

Activity
About

In-Memory Logical Data Warehouse for accelerating Machine Learning Pipelines on top of Spark and Alluxio - ODSC London 9th October 2016

7 years ago • 359 Views

Gianmario Spacagna

Presentations

Parallel Tuning of Machine Learning Algorithms, Thesis Proposal

TunUp final presentation

Robust and declarative machine learning pipelines for predictive buying at Barclays

Logical-DataWarehouse-Alluxio-meetup

In-Memory Logical Data Warehouse for accelerating Machine Learning Pipelines on top of Spark and Alluxio - ODSC London 9th October 2016

Anomaly Detection using Deep Auto-Encoders

Managers guide to effective building of machine learning products

Tech leaders guide to effective building of machine learning products

Latent Panelists Affinities: a Helixa case study

BUILDING Q&A EDUCATIONAL APPLICATIONS WITH LLMS - MARCH 2024.pdf

Likes

Why Deep Learning Works: Self Regularization in Deep Neural Networks

Lessons Learned Running Hadoop and Spark in Docker Containers

Hundreds of queries in the time of one - Gianmario Spacagna