Summary
Overview
Work History
Education
Skills
Languages
Programming Skills
Personal Information
Timeline
Generic

STEFANO TOLOMEO

Milan

Summary

Experienced Data Scientist and MLOps Leader with a proven track record of over 8 years in crafting advanced analytics solutions that address complex business challenges. I excel in not only comprehending the intricacies of business problems but also in orchestrating data-driven strategies to extract maximum value. My career is distinguished by a strong foundation in quantitative skills, coupled with hands-on expertise in cutting-edge technologies such as Snowflake, Python, DBT, AWS, Sagemaker etc. In addition, I have demonstrated exceptional leadership capabilities through managing teams, leading complex technical projects as MLOps initiatives, and delivering actionable insights to drive data-driven decision-making across organizations.

Overview

8
8
years of professional experience

Work History

Senior Data Scientist MLOps

GoStudent
08.2023 - Current
  • Built MLOps framework at GoStudent from the ground up,
    leveraging AWS technologies, SageMaker, Lambda, and API Gateway. Implementing robust CI/CD pipelines for
    streamlined model deployment.
  • Developed and deployed a model for estimation of lead conversion probability, using python with XGboost classifier. The model has been successfully integrated with hubspot for real time prediction (< 1 minute delay from lead creation event) as well as with Google Conversion API to optimize marketing expenditure
  • Deployed churn model using python with Random Forest. The model has been successfully integrated with Customer.io, allowing Customer Success time to personalize retention strategy
  • Worked an MVP for a Chatbot leveraging lesson transcript using llama index framework. This product include RAG using the transcript, levaraging ChromaDB vector database. The MVP has been successfully deployed internally and is currently under beta testing

Data Lead

Casavo
11.2020 - Current
  • Managing a team of 4 people (data engigneer, analyst and scientist) and being the main responsible for hiring – performing interview, supporting hr team in job description definition
  • Built machine Learning model for Risk Assessment of Investment using Python – built the first predictive model for business used to estimate the risk of real estate investment – designed the methodology from scratch – being the only administrator of the repository working managing and coaching 3 junior resources
  • Built machine learning model to predict sale time using Python – built predictive model to estimate the sale time of proprietary inventory, used survival probability model – designed model and coding from scratch
  • Building BI data pipelines for analytics using DBT – built pipeline from internal tools as well as commercial tool as hubspot, fivetran and google analytics – advanced data modelling using dimensional modelling and incremental models - being co-administrator of the data transformation repository - managing and coaching 2 resources
  • Setup BI reporting area from scratch using Tableau and Metabase – built the main company dashboard related to operation analytics and real estate market data analytics – managing and coaching 2 resources
  • Additional activities as organizing workshop on Data, supporting business with automated tools in python, drafting first data governance in the company.

Data Analyst / Scientist - Marketing & Growth

Glovo
10.2019 - 11.2020
  • Dashboard design for most important growth metrics – data modelling DBT, Looker, python (dash/plotly library), PySpark, managing and mentoring junior resources
  • Contributed to the product recommendation system –item-item collaborative filtering model – Python - managing and mentoring junior resources
  • Forecast of business volumes using statistical models as ETS, ARIMA, ARIMAX, Theta Model – R
  • Estimation of causality impact for marketing campaigns – Casual Impact model, Regression Model, A/B Testing design and evaluation - Python, Jupyter Notebook - managing and mentoring junior resources
  • Contributed to the internal Propensity Model – model to estimate probability of customer purchase – xgboost model - Python.

Senior Quantitative Analyst / Data Scientist

Pwc UK
03.2018 - 07.2019
  • Built Customer Rating Model using Python – built challenger model of customer rating model using xgboost machine learning model – used libraries scikit-Learn, numpy, pandas, matplotlib, pyplot, scipy
  • Built Clustering Model for Customer Segmentation using Python – built a prototype of customer segmentation models for a digital bank – used k-means algorithm
  • Model documentation and model testing of IRBB models (Based in Frankfurt for top tier German Bank)
  • Validation and testing of exotic equity derivatives pricing models – Montecarlo models, PDE models, test coding in C# - management and coaching junior resources (for top tier US Bank)
  • Model Validation FRTB market risk internal models – Test design, test coding in Python, full standardised model coding - management and coaching junior resources (Based in Amsterdam for top tier Dutch Bank).

Quantitative Analyst

KPMG Italy
03.2017 - 02.2018
  • Validation and implementation of VaR model for energy trading firm – Montecarlo method, Historical method, time series analysis, VaR Model coding in VBA
  • Pricing complex credit derivatives – stochastic interest rate models, Gaussian and Archimedean copulas for default correlation, stochastic LGD using different distributions, model coding in Matlab
  • Calibration of financial and credit risk in compliance with Solvency II regulation – statistical tests, PCA analysis, calibration benchmark coding in Python.

Analyst (Market and Counterparty Credit Risk)

Deloitte Italy
12.2015 - 02.2017
  • Impact study FRTB pricing models – quantitative data analysis, pricing CCS in excel, use of Quantlib library.

Education

MSc in Finance -

University of Padua
03.2016

Erasmus Programme in Czech Republic
07.2013

Skills

  • Python

  • Machine Learning

  • DBT

  • SQL

  • Analytics Engineering

  • Tableau

  • AWS Sagemaker

  • CI / CD Pipelines

  • AI Framework: Llama Index

  • AWS Cloud

  • Terraform

Languages

Italian
English
Spanish
French

Programming Skills

Python, Excellent, R, Good, C#, Good, Python, Excellent, Excellent, Excellent, Excellent, Good, Intermediate, Very Good, Very Good, Basic, Excellent, Good, Basic

Personal Information

Title: Senior Data Scientist

Timeline

Senior Data Scientist MLOps

GoStudent
08.2023 - Current

Data Lead

Casavo
11.2020 - Current

Data Analyst / Scientist - Marketing & Growth

Glovo
10.2019 - 11.2020

Senior Quantitative Analyst / Data Scientist

Pwc UK
03.2018 - 07.2019

Quantitative Analyst

KPMG Italy
03.2017 - 02.2018

Analyst (Market and Counterparty Credit Risk)

Deloitte Italy
12.2015 - 02.2017

MSc in Finance -

University of Padua

Erasmus Programme in Czech Republic
STEFANO TOLOMEO