Institution profile

Miguel Hernandez University

Academic institutioneurope · es
Official website
Research library50linked papers
Opportunities0open roles
Selected work

Representative Papers

Integration of LSTM Networks in Random Forest Algorithms for Stock Market Trading Predictions

Nov 20, 2025

This paper addresses the challenge of jointly modeling temporal technical indicators and static fundamental information—tasks poorly handled by single-model approaches. We propose a hybrid LSTM–Random Forest forecasting framework: an LSTM module captures deep sequential patterns from price time series, while a Random Forest integrates technical indicators (e.g., MACD, RSI) with macroeconomic and firm-level fundamentals; crucially, it incorporates a feature-importance-driven technical indicator selection mechanism. Evaluated on 10-day return prediction for international public companies, our method significantly outperforms baseline models—including standard LSTM, Random Forest, and XGBoost—in both predictive accuracy (p < 0.01) and out-of-sample Sharpe ratio. Results demonstrate that heterogeneous data fusion yields substantial, statistically robust gains in quantitative trading performance. The framework offers a novel, interpretable, and robust paradigm for intelligent trading powered by multi-source financial data.

2 citationsRead paper
Recent publications

Latest Papers

Execution Timing Control for Deterministic Task Offloading in the IoT-Edge-Cloud Continuum

Aug 01, 2026

Existing task offloading approaches typically determine only the execution location while neglecting the start timing, often leading to transient congestion and failing to meet deadlines for delay-sensitive IoT applications. This work proposes a deterministic offloading mechanism that jointly optimizes both execution location and start timing, incorporating scheduling time into offloading decisions for the first time. By leveraging task slack time, the method enables spatiotemporal co-scheduling across the IoT–edge–cloud continuum through delay-budget-based scheduling, joint spatiotemporal resource optimization, and deterministic service guarantees. Experimental results demonstrate substantial performance improvements: deadline satisfaction rates increase by up to 70%, communication overhead is reduced by 40%, peak computational load decreases by 15%, and average execution time is shortened by as much as 77%.

0 citationsRead paper