WorksComputer Science
From Prediction to Action: An Execution-Aware End-to-End Machine Learning Framework for Structured Investment Decision Support
Abstract
Financial machine learning is widely used for market prediction, but many existing studies formulate trading as a directional forecasting problem and stop at predicting whether prices will rise or fall. Such predictions are difficult to translate directly into practical trading decisions, which also require execution rules, risk controls, and clearly defined actions. To address this gap, we propose an end-to-end machine learning framework for structured investment decision support. The framework integrates multi-asset market data, execution-aware label construction, feature engineering and refinement, specialist predictive models, and ensemble learning. Rather than defining learning targets solely according to future price direction, the proposed execution-aware formulation considers realised trading outcomes under predefined stop-loss and take-profit rules. Model outputs are subsequently converted into structured trading recommendations comprising trade direction, entry price, stop-loss, take-profit, and risk-reward ratio. The framework is evaluated using time-aware forward testing, with results showing that execution-aware labelling improves risk-adjusted trading performance over conventional directional labelling and that the integrated framework outperforms a simpler single-model baseline across key trading metrics. An automated cloud-based implementation further demonstrates the operational feasibility of the proposed approach. Overall, the findings suggest that closer alignment between predictive modelling, execution logic, and structured decision generation can improve the practical value of machine learning for financial trading.