Dive into the future of financial analysis and the power of uncertainty quantification using conformal prediction techniques, applied through the robust capabilities of Nixtla library. Gain insights into how this tool provides reliable predictive intervals, enhancing decision-making in volatile markets. Advantages and Fundamentals concepts of Conformal Prediction: Explore the impact of conformal prediction on financial time series forecasting. This talk will introduce the fundamentals of conformal prediction, highlighting its ability to provide reliable uncertainty quantification by generating predictive intervals that encompass real market behaviours. In this way conformal prediction allows investors to make informed decisions despite inherent market volatility. Nixtla library and practical example of a financial time series: To bring theory into practice, Claudio will present the Nixtla library, which simplifies the implementation of conformal prediction, and walk us through a use case using Yahoo! Finance's API with a comparison of TimeGPT against several statistical and machine learning models. Streamlit App: Develop a Streamlit App for a general Stock Market Forecasting, supported by a Stock Agent Analysis built with pyautogen

First, we explore the core concepts of foundation models, such as pretraining, transfer learning and fine-tuning. Second, we take a look at the advantages and disadvantages of foundation models in time series forecasting. While they can speed up the modeling and inference process, they might also not be the best solution for a particular project, meaning that we must still have a certain expertise to use them correctly and compare them with other methods. Then, we explore some of the major contributions to the field, including TimeGPT, Chronos, Moirai and TimesFM. We quickly discover their architectures, their capabilities and their limitations. Finally, we see TimeGPT in action to demonstrate how a foundation model can be used and how it compares to traditional methods.