High-Frequency Financial Time Series Return Prediction Oriented Towards Transaction Costs: A Hierarchical Ensemble Learning and Regularized Meta-Learning Framework Incorporating Microstructural Features of Broussonetia Papyrifera
Bibliographic record
Abstract
This paper evaluates a transaction cost-aware return prediction framework for minute-level high-frequency CSI 300 stock index futures data from 2017 to 2025, comprising 518,873 minute bars. Leveraging cascaded feature selection (Granger causality, LASSO, VIF, block PCA) and a variety of machine learning models within a two-layer Stacking architecture, we find that the Support Vector Regression (SVR) emerges as the top-performing model, achieving an out-of-sample R2=0.982 mean absolute error = 0.1631, directional accuracy = 96.2% and an annualized Sharpe ratio = 10.0. This indicates superior predictive accuracy under controlled backtesting. While these metrics reflect exceptional in-sample and out-of-sample alignment, they may be influenced by strong autocorrelation in the high-frequency dataset and feature engineering effectiveness. Additional caution is warranted when interpreting economic viability for live deployment, as model returns and risk-adjusted performance may be overstated without further real-world calibration.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".