Claudio Sartori

Internship for thesis preparation

Internship for thesis: Iconsulting, students can contact Ing. Federico Ravaldi

1. Design and implementation of an optimization algorithm in fashion industry to proactively manage the sorting of finished goods from suppliers and the packaging of shipments to wholesalers. The solution should include an algorithm that adapts to variable workloads and reduces manual labour by recommending the best strategies for customer operations.
2. Experimentation of the principles of the new Data Mesh paradigm in the context of Public Health, to make administrative and clinical data interoperable among various local agencies. The experimentation aims to deepen the concepts of marketplace, data product, and shared governance in a concrete context with suitable peculiarities and these types of paradigms.
3. Large Language Models (LLM) to support Data Governance for automating manual metadata enrichment processes. In data governance, the comprehensive structuring of metadata to enable proper governance and understanding of Business Analytics systems requires a non-trivial effort both at the technical level (IT Departments) and from end users (Business Units). The experimentation aims to understand how through the use of AI techniques an initial intelligible mapping of metadata can be generated, reducing the manual effort and maximizing the return for businesses. As a second step, we will also test these technologies (OpenAI, ChatGPT Enterprise, ...) in the area of querying the metadata map in natural language.
4. Benchmarking on performance and utilization level of Data Lakehouse technologies. A number of technologies that aim to simultaneously leverage the benefits of data lakes and data warehouses to create data architectures that decouple the storage portion from the computation portion and support the world of hyperscalers are gaining a foothold in the market. The experimentation will aim to compare different rising star technologies.
5. Combination of Location Analytics and Machine Learning to support the structuring of public administration services on the ground. Experimentation for a local government in structuring algorithms using enterprise, spatial and external data to optimize services offered to citizens with a view to innovative patient-centric service design.