DATA-DRIVEN MODELS FOR INVESTMENT

General Learning goals: At the end of the course, students must have developed both technical skills in the financial and theoretical fields to model the markets, and have the ability to communicate them clearly. Students of Data – Driven Models for Investment will have to reach three main targets: Knowledge of Finance and AI principal theoretical concepts. Coding skills to devise an algotrading strategy. Communicating skills. The course is divided in such a way as to achieve each of the goals in the following way; Frontal lectures to explain theory. Practical Python exercises. Presentation of case study results Specific Learning Goals: The conveyed hard skills include: Ideation of a systematic trading strategy. Keep under control the complexity of financial data. Acquire a general overview of Financial Markets. Introduction to Quantum Computing The transmitted soft skills include: Communicate your ideas in front of an audience. Lateral thinking to manage complex problems. Team working and leadership. Multilateral way of problem solving.

The students must know basis of linear algebra, statistics and Python language. No previous knowledge of finance is required.

The knowledge transmitted by the course to students involves: Modeling financial markets with complex methods from mathematics and fuzzy logic Using Artificial Intelligence to optimize a systematic trading strategy in Python Introduction of Quantum Computing The students will be able to distinguish important information for the creation of an algo -trading strategy and financial markets modeling. They can look forward to careers as financial analysts, quantitative researchers or quantitative analysts in hedge funds, investment banks or quantitative funds.

Fuzzy Logic and Financial Markets (12 h) Artificial Intelligence and Financial Markets (12 h) Introduction to Quantum Computing (12 h)

The course materials will be based on collection of top scientific articles and book reports. Articles and other materials (cases) will be available through the Luiss Learn platform.

Lectures will be divided in the following way: 30 hours: Frontal lectures with possibility of questions about the three main topics about the course: Fuzzy Logic, Reinforcement Learning and Introduction with Quantum Computing 6 hours: In these hours, we will show to the students three different examples of Python Algorithm about the three main topics. These lessons will be interactive as in the first part of the lesson we will show an example of an algorithm on Python leaving them an optional exercise to be carried out in the following two weeks from the request. Students will be favored in terms of grade on the exam according to the methods that we will specify in the assessment method part.

The achievement of the intended learning outcomes will be verified in three different steps: During the course: At the end of each of the three Python exercitations, the committee will show to the students a code, as described in the teaching methods with the aim of awarding bonus points for the exam. Each student will have a different bonus at the final exam based on the quality of the problem solving resolution. 0 points: the student does not promote any ideas about the resolution of the task. 1 point: The student proposes a possible resolution but the commission does not consider them interesting. 2 points: The student proposes improvements and the commission considers it very interesting and useful to devise new ideas of trading strategies. To reach 1 point, students can also just propose their ideas without writing the attached code, to reach 2 points students will have to send a detailed proposal and code in .ipynb format via email within two weeks of assignment. Students can organize themselves in groups or individually, it would be preferable individually. The maximum score obtainable by each student is therefore 6 points. Case study group: Students will have to work on a case study proposed by the company. This case study will be the creation of an algotrading strategy based on one of the three main topics of the course. Students will be divided into 3/4 groups based on the number of enrollements. The evaluation will be carried out both on the basis of the technical presentation and the ability of the candidates to discuss and argue their results. On the day of the exam the groups will show one at a time their presentations that will have a maximum time limit of 30 minutes. The committee will evaluate each presentation within a vote between 0 and 15. At the end of this phase, the next group will show its own presentation, until the end of the groups. Final oral exam: The final oral exam will be individual, regarding all the theoretical concepts explained during the course. The commission will ask questions on the theoretical meaning of the formulas explained. The committee will attribute an assessment based on the comprehension of the theory from the students and the ability to discuss them. The vote for the oral exam will be up to 15 points. The maximum score obtainable by each student is 36; each grade above 30 will be 30L.

The thesis will be assigned (upon specific request to the instructor) to students who demonstrate a serious and motivated interest to the course subjects.

No, the syllabus does not cover sustainability topics.