Convolutional Neural Network – Based Algorithm for Currency Exchange Rate Prediction
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
The foreign exchange market is one of the complex monetary markets in the world. Each day trillions of dollars are traded in the FOREX market by banks, retail traders, corporations, and individuals. It is very challenging to predict the price in advance due to the complex, volatile and high fluctuation. Investors and traders are constantly searching for innovative ways to outperform the market and increase their profits. As an outcome, forecasting models are continually being developed by scholars around the globe to accurately predict the characteristics of this nascent market. This study intends to apply the Random Forest (RF) approach to Convolutional Neural Networks, which involves two key steps. The first step is starting with feature selection using Convolutional neural network.The attention layer is then employed to assign weight.The random forest strategy is designed in the second stage to generate high-quality feature subsets. Thus the better result generated by CNN-RF model. Actually, this strategy combines the advantages of two different strategies to produce an outcome that is more consistent with what exchange market decision-makers anticipate happening in the exchange market.The main currency pairs considered in this study's proposed model for predicting exchange rates five and ten minutes in advance are the British Pound Sterling (GBP) against the US Dollar (USD), the Australian Dollar (AUD) against the US Dollar (USD), and the European Euro (EUR) against the Canadian Dollar (CAD) are also used to evaluate the performance of the proposed model. In compared to the other three models (Multi-Layer Perceptron, Autoregressive Integrated Moving Average, and Recurrent Neural Network), CNN-RF yields better results. This conclusion has been backed by a large body of empirical research, which also suggested that this methodology be regularly used due to its high efficacy.
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.
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 | 0.009 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.003 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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 it