Daniele Zago
Data Scientist

Currently working as a Data Scientist at OPTIT S.r.l., Bologna 🇮🇹
My background is in industrial statistics, with expertise in online outlier detection and stochastic optimization. I am passionate about solving complex problems and developing data-driven solutions.

  Contact   Linkedin   Github   CV 🇬🇧   CV 🇮🇹
Profile Picture of Adrián Moreno (@zetxek), working side by side with a colleague: sitting on a desk, while looking at a screen

Who am I?

I am a statistician that applies data-driven methodologies to develop solutions to solve complex problems. I am a fast learner with the passion of discovering new things.

I have pursued a doctoral degree with the aim of deepening my knowledge, and I have experience in statistical consulting as well as software development. Most the projects I was involved in required efficient algorithmic solutions, coupled with the development of user interfaces to allow user-friendly applications.
The things that I look forward the most in a problem are challenges and novel solutions. Because of this, I have worked on a range of different topics, such as 3D meshes, stochastic optimization, and efficient algorithms.

Education

University of Padova -- Statistical Sciences
2021 — 2024   Doctor of Philosophy (Ph.D.)
2019 — 2021   Master of Science (M.Sc.)
2016 — 2019   Bachelor of Science (B.Sc.)

Experience

Experienced in designing advanced statistical algorithms, specializing in real-time outlier detection and stochastic optimization.
Proven ability to deliver data-driven solutions in consulting projects, translating technical requirements into actionable strategies, and consistently meeting client expectations.

Projects

Monitoring of complex geometrical shapes

I developed an innovative statistical quality control method for detecting shape defects in complex geometries obtained via additive manufacturing. I introduced a novel nonparametric control chart based on kurtosis analysis which provides superior defect detection for 3D-printed objects compared to existing approaches.

A software for modern statistical process monitoring

I developed a software package in Julia designed for advanced statistical process monitoring. This package integrates state-of-the-art algorithms with modern control charts to monitor complex data structures, including sequential data, functional data, and networks.

The software is designed for real-time monitoring and early detection of anomalies, with versatile applications across various industries.

A paper detailing the versatility of the package is scheduled for publication in 2025 on the Journal of Statistical Software.

Source code  

A doubly-stochastic constrained optimization algorithm

I designed a novel stochastic optimization algorithm with stochastic constraints, aimed at optimizing control chart tuning parameters with greater efficiency compared to traditional numerical methods. This innovative approach has been published in the Journal of Quality Technology.

Journal article  

Alternative parameter learning schemes for monitoring process stability

I formalized the theoretical behavior of parameter learning schemes in relation to outlier detection performance in control charts. This work enabled the generalization of alternative parameter learning methods, leading to a more efficient and accurate detection scheme compared to traditional approaches. This work has been published in Quality Engineering.

Journal article