BUSINESS AND MARKETING ANALYTICS

The main objective of this course is to give a basic introduction to artificial intelligence (AI) and its subsets machine learning (ML) and deep Learning (DL). Through a low coding tool, the students are given a practical understanding of the methods being taught, in particular through making their own implementations of several of the methods. The course covers supervised classification based on e.g., artificial neural networks (deep learning), as well as unsupervised learning (clustering), regression, optimization (evolutionary algorithms and other search methods) and reinforcement learning, in addition to design of experiments and evaluation. Students also receive an introduction to philosophical fundamental problems and ethical questions related to ML/AI, as well as the field's history. A significant part of the course will be devoted to using these tools to solve a variety of real-life problems.

Basic knowledge of statistics and basic knowledge of computer science.

Basic introductory-level knowledge in using Machine Learning and Deep Learning algorithms for solving real-world problems in financial, capital market scenarios and recommender system.

The course focuses on theoretical foundations, techniques, methodologies, and applications of artificial intelligence, in order to contribute to the diffusion and advancement of knowledge and skills on this subject and its applications, thus promoting technological innovation and fostering the economic and social development. In particular, the course will cover the following topics: - Introducing to the notion of Artificial Intelligence, Big Data, Machine Learning and Deep Learning - Introducing basic knowledge about Machine Learning and Deep Learning Algorithms - Solve real-use case task: applications for evaluating the consumer behavior (recommendation system and behavioural understanding) application to capital market - Basic knowledge about the framework of Ethical AI: robustness, interpretability, fairness and accountability - Design of multimedia systems. Augmented, virtual and mixed reality. - Low-coding solutions for Artificial Intelligence and Deep Learning. - Use cases and applications of the topics.

Agresti, C. Franklin (2014) Statistics - The Art & Science of Learning from Data (3th edition –International Edition), Pearson, Essex, England. Pattern Recognition and Machine Learning (Information Science and Statistics) 0387310738 I Springer-Verlag A Christopher M. Bishop 2006

• Lectures (40%) • Lab sessions and Project work (40%) • Seminars with companies (20%) • These activities will be planned to allow students to practically realise the solutions of the problems outlined during the theoretical lectures, using low-coding tools. Supporting teaching materials (handouts, video tutorials, dataset, exercises and demos) will be provided.

Competences will be assessed via on team evaluation, which is based on 70% PW performed from week 3 to the end of the course, 30% on Final project (Hackathon)

• Project work evaluation (mid-term examination) • Final Hackaton with real-use case task (Final evaluation)