Main
Core Skills
High experience in time series modeling and forecasting, ML modeling and text mining
Languages
Marco Zanotti
I am a data scientist with broad knowledge in time series analysis, forecasting, anomaly detection, and econometrics.
I specialized in developing and enhancing business forecasting processes and practices. Over the years I developed and contributed to core forecasting systems in sectors like e-commerce fashion, airline, tourism and travel. I also guided and mentored junior colleagues in developing predictive models that enable accurate forecasting.
I am passionate about advancing the field of forecasting and fostering collaboration between academia and industry. I do academic work in forecasting, and I am a member of the International Institute of Forecasters.
Recently I have enjoyed teaching professionals and university students about time series analysis, machine learning, programming, and statistics.
Professional Experience
Researcher, Forecasting Specialist
iqast - Software - Full remote
Hamburg, Germany
2026 - 2026
- Contributed, with the research team, to improve the company’s forecasting software
Data Scientist, Forecasting Specialist
Wanan Luxury - E-commerce Fashion - Full remote
Rome, Italy
2025 - 2024
- Led the company’s time series forecasting projects
- Coordinated and contributed to the development of a forecasting tool to predict future demand for tens of thousands item-level (SKUs) time series across several markets worldwide, and with different product hierarchies, resulting in increased forecasting accuracy and efficiency
- Integrated probabilistic methods to support more informed decisions
- Designed and developed an app for evaluating forecasting experiments, enhancing reliability of the analyses
- Provided mentorship to junior colleagues, supporting their professional growth and development in the field of forecasting
Data Scientist
Blogmeter - Digital Services - Hybrid
Milan, Italy
2024 - 2021
- Integrated machine learning solutions into company’s applications
- Developed an anomaly detection solution to promptly communicate relevant events to the clients
- Coordinated the Product team
Data Scientist
T-Voice - Digital Services - Full remote
Milan, Italy
2021 - 2020
- Contributed to the development of an AI platform for the analysis of textual data
- Effectively incorporated text data into forecasting models
- Coordinated the R&D team
Junior Data Scientist
Uvet Amex GBT - Tourism and Aviation - Hybrid
Milan, Italy
2020 - 2017
- Developed and maintained diverse statistical and machine learning models to predict: sales at different aggregations to support strategic decisions; daily inbound calls to optimize scheduling hours; air passenger demand over several destinations to support aircraft planning; business car rental demand to support fleets management
- Successfully improved the approach to forecasting, resulting in a significant reduction of errors and facilitating the faster adoption of machine learning solutions by the business
- Implemented an anomaly detection system to signal possible congestions in the company’s reservation platform
- Developed econometric models to measure key drivers of business travel and tourism
- Supported automation processes implementing OCR solutions
Programming
BI & Visualization
Databases
Versioning
CI / CD
Cloud
Project Management
Operating Systems
Teaching Experience
Adjunct Professor
University of Milan - Hybrid
N/A
current - 2019
I teach forecasting, machine learning, coding, and statistics.
Business Consultant
Business Consultancy - Hybrid
N/A
current - 2019
I offer consultancy and training about forecasting, machine learning, and the development of business specific statistical models.
Awards
International Symposium on Forecasting Award
International Institute of Forecasters
Beijin, China
2025
Certificates
• Certified Forecaster and Demand Planner
• High-Performance Time Series Forecasting
• Designing Forecasting Pipelines for Production
• Deep Learning for Sequence Modelling and Times Series
• Python for Machine Learning and APIs
• Python for Data Science Automation
Spoorts & Hobbies
I was a footballer. I played in Italian minor championships until 22.
Now I practice kitesurf, an amazing waterboard sport, and I do canicross with my little friend Milo.
I like manga, boardgames, videogames, curling and footgolf.
I love listening folk and country music.
Made with R and pagedown
Last updated on April 2026
Education
Ph.D., Statistics
University of Milano-Bicocca
Milan, Italy
2026 - 2022
Research on time series forecasting, cross-learning, forecasting stability, time series foundation models (LLMs), MLOps, and green AI
Post-graduate, Data Science for Economics, Business and Finance
University of Milan
Milan, Italy
2018
M.Sc., Economics and Finance
University of Milan
Milan, Italy
2017 - 2015
B.Sc., Political Sciences and International Relations
University of Parma
ERASMUS, University of Lapland, Rovaniemi, Finland
Parma, Italy
2014 - 2011
Personal Competences
Organisational and Management
N/A
N/A
N/A
- Project management: I coordinated the development of different projects, from analysis to implementation
- People management: I coordinated the activities of junior colleagues, supervising and guiding in their professional develpment
- High relational and communication skills
- High resistance to stress
- Since 2020 I proficiently work from remote
Publications
Sustainable forecasting with artificial intelligence: The role of retraining frequency
Zanotti, M., In M. Hamoudia, E. Spiliotis, & P. Montero-Manso (Eds.), New frontiers in forecasting with artificial intelligence: Methods and applications. Palgrave Macmillan
N/A
2027
Analyzing the retraining frequency of global forecasting models: towards more stable forecasting systems
Zanotti, M., arXiv
N/A
2026
An evaluation of ensemble strategies for time series anomaly detection
Zanotti, M., Zangirolami, V., Pavesi, F., Springer
N/A
2026
A characterization of Gaussian processes over flat tori
Pavesi, F., Zanotti, M., Zangirolami, V., Springer
N/A
2026
Safe Exogenous State Reinforcement Learning for water tank system
Zangirolami, V., Pavesi, F., Zanotti, M., Springer
N/A
2026
Do Short Exposure and Systematic Risk Exposure Drive Asymmetries in the Disposition Effect?
Mazzucchelli, L., Zanotti, M., et al., arXiv
N/A
2026
On the retraining frequency of global models in retail demand forecasting
Zanotti, M., Machine Learning with Applications, 22, 100769
N/A
2025
The cost of ensembling: Is it always worth combining?
Zanotti, M., arXiv
N/A
2025
dispositionEffect
Zanotti, M., Mazzucchelli, L., CRAN, R Software
N/A
2021
Conferences & Seminars
Analyzing the retraining frequency of global forecasting models: towards more stable forecasting systems
International Symposium on Forecasting
Montreal, Canada
2026
An evaluation of ensemble strategies for time series anomaly detection
SIS-FENStatS
Rome, Italy
2026
Do global forecasting models require frequent retraining?
International Symposium on Forecasting
Beijin, China
2025
Computing Disposition Effect on Financial Market Data
useR! 2021 Conference
Remote
2021