The work investigates the application of Quantum Machine Learning (QML) techniques - with particular emphasis on the Quantum Reservoir Computing (QRC) paradigm - to time-series forecasting in the financial domain. Quantum reservoirs exploit the high-dimensional nature of Hilbert spaces and the intrinsic dynamics of quantum systems to process temporal data, offering a potentially powerful alternative to classical approaches. The project involves the design and implementation of QML models based on quantum reservoir architectures, the execution of simulations on different quantum computing backends, and a systematic comparison with classical forecasting methods and benchmarks. Both idealized and realistic scenarios are considered in order to assess the impact of noise and hardware constraints on model performance.