Course Topics
Module 1 – Financial Analytics with AI • Introduction to Python and data structures for financial data (pandas) • Data acquisition, cleaning and exploratory analysis of large financial datasets • Financial modelling and trend forecasting with Python • Interaction with large language models (LLMs) and generative AI for financial analysis • Introduction to blockchain technology and cryptocurrencies Module 2 – Blockchain, AI and Textual Methods • Statistical methods in accounting: linear, polynomial, step, spline, local regression, GAM models • Fraud prediction: logistic regression, Benford's Law, and the phenomenon of quadrophobia • Audit analytics and anomaly detection • Dimensionality reduction: PCA and related techniques • Matching methods: propensity score matching and entropy balancing • Natural language processing: LDA topic modelling and textual analysis • Generative AI in accounting: automated topic labelling and AI-assisted analysis • Blockchain in accounting: case studies (FTX, TerraLuna, Beefchain, and others)

Teaching format
M1 - Frontal lectures in standard classroom with examples and exercises. Students attend with their own notebook or a computer borrowed from the library and interact with LLM in their own way. Homework is assigned and corrected in the next lesson. Final mock-up exams are done together in the last lessons. M2 - A combination of lectures, data-driven case discussions, and guided empirical exercises. Real-world accounting and auditing datasets are used to illustrate methods. Guest practitioner presentations and discussion of academic research papers may be incorporated. Both modules encourage active participation. Students are expected to review assigned material prior to class and engage critically with examples and cases.

Educational objectives
ILO (Intended Learning Outcomes) ILO 1 – Knowledge and Understanding ILO 1.1 knowledge and understanding of economic and financial communication directed at stakeholders at both national and international level ILO 1.2 knowledge and understanding of economic and business models and performance measurement for planning and management control, as well as of models and methods of internal and external auditing ILO 1.3 knowledge and understanding of the planning and evaluation of new investments from an economic and financial perspective ILO 1.4 knowledge and understanding of the fundamentals of corporate finance for the correct application, for example, of decision-making models and of financial data and risk management in treasury management ILO 1.5 knowledge and understanding of economic and business models and tools for the management of firms, both family-owned or small-sized enterprises and internationally operating companies ILO 1.6 knowledge and understanding of the design and management of institutional and organisational structures related to corporate governance systems ILO 1.7 knowledge and understanding of business tools and processes developed to recognise, understand and drive change and to manage the impact of transitions on organisations ILO 1.8 knowledge and understanding of strategies for effective communication within organisations and towards different stakeholders ILO 1.9 knowledge and understanding of management topics characterising the profession of financial analyst, portfolio manager, risk manager and consultant ILO 1.10 knowledge and understanding of basic forecasting models to carry out integrated economic and financial analyses, also using econometric methods for time series and multivariate analysis ILO 1.11 knowledge and understanding of Big Data analysis techniques to support and integrate business decision-making processes ILO 2 – Applying Knowledge and Understanding ILO 2.1 ability to develop and integrate the results of economic and financial communication into business decision-making models ILO 2.2 ability to design and manage corporate restructuring processes and other extraordinary transactions ILO 2.3 ability to identify, evaluate and manage investments in financial markets ILO 2.4 ability to design coherent financial management strategies in firms or financial intermediaries, competently applying acquired knowledge in risk management techniques, asset valuation and derivatives ILO 2.5 ability to understand the evolution of financial markets and changes in the international macroeconomic context ILO 2.6 ability to analyse economic, managerial and financial variables in support of decision-making in firms and financial intermediaries ILO 2.7 ability to frame and critically evaluate situations and problems on the basis of scientific methods from a multidisciplinary perspective, thanks to training that integrates business, economic, legal, financial and statistical-mathematical disciplines ILO 3 – Making Judgements ILO 3.1 ability to apply acquired knowledge to make managerial and operational decisions and to solve administration and finance problems of firms, intermediaries and financial markets, jointly considering multiple analytical perspectives, including economic, legal, financial, strategic and managerial perspectives ILO 3.2 ability to select data and use appropriate information to describe problems related to the management of firms, intermediaries and financial markets ILO 3.3 ability to relate models and empirical evidence in the study of firms, intermediaries and financial markets ILO 4 – Communication Skills ILO 4 ability to communicate effectively, both orally and in writing, the specialised contents of individual disciplines, using different registers depending on the audience and communicative or educational objectives, and to assess the educational impact of such communication ILO 5 – Learning Skills ILO 5.1 ability to identify thematic connections and establish relationships between different cases and analytical contexts ILO 5.2 ability to frame new problems in a systematic way and to generate appropriate taxonomies ILO 5.3 ability to develop general models starting from the phenomena analysed

Additional educational objectives and learning outcomes
Knowledge and understanding: Students will develop a working knowledge of modern AI and computational methods as applied in accounting and finance, including both the theoretical underpinnings and practical implementation. They will understand how these methods are used in academic research and professional practice. Applying knowledge and making judgements: Students will be able to conduct end-to-end empirical analyses — from data collection and preparation to model estimation, interpretation and presentation. They will develop the critical capacity to identify appropriate methods for specific problems and to evaluate the quality and limitations of results. Communication and learning skills: Students will be able to communicate analytical findings effectively, both in oral presentations and written reports. They will also build the self-directed learning skills necessary to keep pace with rapidly evolving AI and data science tools.

Assessment
Module 1 – Financial Analytics with AI (50%): 42% Assessment based on a practical examination involving Python programming for financial data analysis (including interaction with generative AI tools), 8% a written component on blockchain technology. Module 2 – Blockchain, AI and Textual Methods (50%): Assessment based on a combination of participation in case discussions, written assignments and/or a final examination. For attending students, the final grade will be a mixture of participation in case study discussions/presentations/written works and mid-term assignments and exam(s) (ILOs 1-5). For non-attending students: written final exam (100%) (ILO 1-5). Detailed point breakdown for individual assignments and exam modalities will be provided in the first lecture.

Evaluation criteria
Grading reflects the quality of analytical reasoning, the correctness and efficiency of technical implementations, and the ability to interpret and communicate results clearly. Specific rubrics for each assessment component will be distributed at the beginning of the course prior to the relevant assignment. Grading weights will reflect the amount of class hours dedicated to each topic and will be communicated at the beginning of the course. For Module 1, particular weight is given to solutions that are optimal, versatile and well-documented. Errors traceable to unchecked AI-generated output are taken into account in the evaluation. For Module 2, analytical rigour, correct application of statistical methods, and critical interpretation of results are emphasized.