GS-MultiRC: Multi-step Reservoir Computing Leveraging Grid Search for Stock Indices Prediction
Bibliographic record
Abstract
Stock market prediction plays a crucial role in investment decision-making, portfolio management, and risk assessment, significantly impacting financial stability and economic growth. Accurately forecasting stock prices, which are chaotic and nonlinear, has become a main point of financial research. Deep learning approaches, such as neural networks and long-short-term memory (LSTM) models, have been more reliable than traditional approaches such as the ARMA and ARIMA models. However, these methods require a lot of computational power, complex fine-tuning procedures, and often overfit, especially with limited or noisy data. Reservoir Computing (RC) has emerged as a potential alternative for financial time series prediction. It uses a fixed, randomly connected reservoir to capture patterns in data, requiring only the output layer to be trained. This design makes RC computationally efficient and simpler to use. However, RC models can struggle with overfitting when the reservoir is too large compared to the data or when the model can not adapt well to unseen data. To address these drawbacks, we propose a multi-step RC model, focusing on popular stock indices, including CSI300, FTSE100, S&P500, and SSE50. Our approach includes a retraining step where the reservoir evolves by forecasting some of the training data and simulating real-world testing conditions. These evolved internal states, affected by prediction errors, are used to retrain the output layer, making the model more robust and less likely to overfit. Our experiments show that our model performs more accurately and efficiently than conventional RC and LSTM models, making it a workable and trustworthy option for stock market prediction. This work contributes to utilizing RC-based approaches in terms of the financialforecasting domain.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".