Deep learning (DL) and deep reinforcement learning (DRL) have moved from “interesting papers” to real, production-adjacent toolkits for systematic trading. From 2018–2025, the literature converged on a few uncomfortable truths: * Prediction ≠ trading: higher directional accuracy doesn’t automatically translate into net performance after costs. * Risk-adjusted objectives matter: optimizing for

Fund flow indicators are attempts to answer a simple question with imperfect market data: is capital accumulating (inflow) or distributing (outflow)? In practice, most “money flow” tools are price–volume transforms that treat volume as a proxy for participation and treat where the close occurs (within the day’s range)