On Predicting Financial Time Series of Various Granularity as an Applied AI Problem

We comprehensively examine the efficacy of LSTM models in predicting financial time series. We evaluate the performance of LSTM networks based on various numbers of units determined by temporal granularity, considering aspects such as prediction accuracy. This study contributes to the ongoing discourse on the role of AI in financial markets, offering a nuanced perspective on the practicality and limitations of LSTM models in this critical domain.