A Supervised Classification System of Financial Data Based on Wavelet Packet and Neural Networks
Bibliographic record
Abstract
The purpose of this paper is to present an automated system to classify financial data patterns as indicators of stock market future upward or downward moves. The classification system uses wavelet packet transform (WPT) for data decomposition and backpropagation neural networks (BPNN) for classification task. Its results are compared to those of a common classification system found in the literature which is based on ordinary wavelet transform (WT) and BPNN. In particular, the WPT is applied to the stock market data to obtain two categories of patterns: (i) approximation coefficients that represent major trend of the original data, and (ii) the residuals of the original data that capture its short-time variations. Therefore, those patterns are both complementary information used as inputs to classify stock market future shifts. For comparison purpose, BPNN and support vector machine (SVM) are separately used to classify patterns. Using S&P500 price index data, simulation results showed that both BPNN and SVM perform better with WPT extracted patterns (residuals and approximation coefficients) than standard approach based on WT approximation coefficients. In addition, BPNN outperform SVM. The WPT-NN based approach for financial data classification is more effective and promising than the standard approach adopted in the literature. The finding supports the adoption of the proposed classification system as an appropriate decision-making system in financial industry to classify financial data for forecasting purpose.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".