Data Science Milan #011

Dear Data Science Milan Community,

Welcome back to our newsletter, bringing you another edition packed with the latest developments, inspiring projects, and invaluable insights from the world of data science!

For this edition, we discover the world of Retrieval-Augmented Generation (RAG). It's an AI framework that combines the strengths of traditional information retrieval systems (such as databases) with the capabilities of generative large language models (LLMs).

RAG works by first analyzing the user's input query to understand the intent and context. It then retrieves the most relevant information from external data sources like databases, APIs, or document repositories. The retrieved data is converted into vector representations to enable relevancy matching with the query. Finally, the relevant information is integrated into the language model's prompt to generate a response that is both rich and up-to-date coherent language.

RAG ability is to leverage existing knowledge effectively, leading to more informative and contextually relevant outputs. However, RAG may struggle with generating truly creative or original content, as it heavily relies on existing data.

There are some techniques to improve the accuracy of RAG architectures:

1. Chunking: involves breaking down the input text into smaller, manageable pieces impacting RAG performance.
2. Re-Ranking: is the process of refining the retrieved results to improve their relevance and accuracy. It involves prioritizing the results based on various criteria, such as semantic similarity or contextual relevance.
3. Query Transformations: involves converting the original query into a different query to retrieve more relevant chunks.

If you want to learn more, go to the knowledge section, where you can find also the link to the last article about the PyCon Italia conference held in the beautiful Florence place.

Data?Science?Milan?events

Generative AI in the Banking industry

AI-powered search in banking knowledge bases - Andrea Galliani, Lorenzo Severini

Retrieval-Augmented Generation (RAG) has emerged as a powerful approach to augment Large Language Models (LLMs) with external knowledge, including internal and private documents. In this context, has been introduced UniMate, an internal search engine to empower bank employees, based on RAG architecture. UniMate enables efficient and smart retrieval of information related to products, processes, and internal procedures. During the discussion, they delved into both engineering and data science aspects, providing an overview of the principal architectural and model choices. Additionally, they have addressed the main challenges associated with developing UniMate in a real-world banking context.

Can LLM help create simulators for reinforcement learning? - Davide Villaboni The application of reinforcement learning in the banking sector presents numerous challenges, with the primary obstacle being the lack of a secure environment suitable for simulating and effectively testing policies. To tackle this issue, the team took a different approach by reframing the problem as a forecasting challenge. The chosen model architecture incorporates a Large Language Model, and initial results suggest that this approach can effectively address Unicredit problem.

Watch the video

Data Science applications in Cybersecurity

Application of Graph Theory To Anomaly Detection in Cybersecurity: an Example - Alberto Mazzetto, Artificial Intelligence Modelling Engineer at Ferrari Racing

The scale and complexity of cyber-attacks have been increasing dramatically in recent years, making it necessary to accompany rule-based detections with statistically principled anomaly detection. Alberto explained how graph theory applies to this problem and reviewed global and local modelling approaches. He demonstrated one possible local approach based on a Bayesian conjugate model, the Dirichlet process, that allows for fast, scalable, explainable computations. He then explored a global-flavoured methodology, based on graph variational auto-encoders, aimed at reducing the number of false positives.

A Data-Driven Approach to Cybersecurity - Luigi De Luca, Data Scientist at Data Reply

In today’s data-driven world, Big Data and Data Science have become indispensable tools in transforming the way we approach complex problems. Big Data and Data Science are very useful in handling large volumes of data to derive actionable insights. As cyber threats continue to evolve, traditional cybersecurity methods have proven to be insufficient in effectively defending against modern attacks. So, Data Analytics plays a crucial role in the field of cybersecurity. Luca explored the benefits that a data-driven approach brings to cybersecurity, with a focus on three use cases that are subcases of anomaly detection: "UEBA", "malware detection" and "DGA detection". For each of these three use cases, he explained the improvements compared to the traditional methods and how to implement the solution.

Watch the video

Alkemy’s GenAI ecosystem

On February 20th, 2024 Marcello Villa presented Alkemy’s GenAI ecosystem and some of the use cases they are working on. Shifting perspective from the clients to the developers, in the second part Davide Posillipo reflected on how the latest Generative AI applications are impacting our field, Data Science, and what we can expect to happen in the future to our profession. As an example of new ways of working, in the final part, Milica Cvjeticanin talked about an unconventional Transformer model. LLMs modern architectures based on Transformers represent an extremely powerful tool for solving a variety of problems. However, these architectures are mostly cited when approaching natural language processing. However, by combining meta-learning, Bayesian Neural Network prior (BNN) and Transformer’s architecture the application field of transformer-based models is expanded so that it solves even classification problems with tabular data. Milica showed an example of these models named TabPFN, which could be concurrent to the best-known Machine Learning algorithms for solving these classical ML tasks, pointing out why this model is something worth keeping an eye on.

Watch the video

Knowledge section

Here are some selected resources:

• PyCon Italia 2024 event
• How to improve RAG performance
• RAG architectures

Be involved!

We want also to remind you that if you like and enjoy our events, you can get in touch with us at [email protected] to be involved in organizing new great online activities.

We are also very happy if you are interested in being a speaker or if you want to share your expertise or experience with the?Data?Science?Milan?community!!!

Wallboard

Would you like to become one of our sponsors and increase your popularity among the?Data?Science?community? Write here

If instead, you would like to promote a message to the wallboard, please contact us and send us your relevant announcements. We will publish them here.