From Kaggle to Enterprise Machine Learning

From Kaggle to Enterprise Machine Learning

In this event, we’ll see the two sides of machine learning in the real world.

Talk #1: Kaggle – State of the art ML

Abstract: Kaggle is the leading platform for competitive machine learning, bought by Google in 2017.

Data scientists from all over the world compete on complex problems and top solutions, evaluated with a 100% objective and robust methodology, get rewarded with large prizes (even over 1.000.000 USD).

The speech will show the relevance of Kaggle in the data science world, cover the mechanics of a Kaggle competition, illustrate some examples and provide hints and tips that are useful to achieve a good ranking.

Speaker: Alberto Danese is Senior Data Scientist in the Innovation & Data Sources team in Cerved, since 2016. After completing his studies as a Computer Engineer, he spent 8+ years in consultancy working mainly for large financial institutions.

Passionate about the whole data science stack: from talking to IT architects and data engineers to define the best practices to put data science in production, to presenting innovative solutions to marketing and sales teams.

And obviously Machine Learning! Alberto has recently entered the top tier of Kaggle data scientists (“grandmaster”), only one in Italy.

Talk #2: Credit Scoring – ML in a regulated environment

Abstract: Different fields of application of data science models are subject to regulations that typically limit the use of complex ML solutions in favor of more conventional and explainable models.

Credit scoring is one of such fields. The speech will introduce the main concepts of credit scoring and deal with data modeling and manipulation techniques (even derived from ML approaches) that are used to achieve higher accuracy, while preserving full compliance with applicable regulations.

Speaker: Giovanni Tessiore is head of “Proprietary Scores and Analytics Innovation” unit in Cerved. He has a degree in Quantitative Methods for Economics.

Giovanni started his activity 17 years ago in Centrale dei Bilanci where he carried out several projects in credit scoring with a special focus on solutions covering many fields and approaches, such as parametric and non parametric statistical methods, bayesian models, montecarlo methods and, of course, machine learning. He has defined the methodology of Cerved Group Score and Rating, obtaining the recognition of Cerved as ECAI and Rating Tool in ECAF. He’s addicted to statistical methods and thinks life is a stochastic process that needs the right model to be understood.

The venue has a limited seating capability, please be considerate and cancel your order if you are not willing to attend so that someone from the waitlist will be able to participate.

Agenda:

18:30 Doors opening

19:00 Data Science Milan community introduction

19:15 Talks

Would you be happy to host one of our events? Increase your popularity and be known from our community by hosting one of our interesting events. Contact us at datasciencemilan@gmail.com, all we ask is a venue and possibly an aperitivo buffet.

If you are interested in doing a lightning talk or want to propose an event, hackathon, panel discussion, roundtable or any sort of initiative please submit your proposal at Call for speakers or get in touch with one of the member of the staff.

About the host:

Cerved

Data runs through our veins. It is our spark of life and our passion. Our data enables us to provide superior services, from credit risk analysis to marketing solutions to managing non-performing loans and bad debt. Working all across Italy, over 30,000 businesses and financial institutions turn to us in all phases of their work. Our group also houses one of the leading credit rating agencies in Europe.

Author:

Follow up
This entry was posted in . Bookmark the permalink.