Bibliographic record
Abstract
In today’s global economy, accuracy in forecasting currency exchange rates is of much importance to any future investment. Currency exchange rates portray non-linear and non-stationary characteristics hence to address these characteristics; this paper proposes a hybrid forecasting model using the Empirical Mode Decomposition (EMD) technique, and the ARIMA model. EMD is used to decompose the raw currency exchange rate data into several intrinsic mode functions and one residual. The process of extracting the IMFs from the data is called the sifting process. EMD was used to detect the moving trend of currency exchange rate data and improve the forecasting success of the ARIMA model. The data were obtained from the Central Bank of Kenya website between the periods January 2005 to May 2017. The best ARIMA model fitted to the raw data before decomposition based on information criterion statistics was found to be ARIMA (1,0,3) for the KShs/AE. Dirham, ARIMA (1,0,1) for KShs/Australian dollar and ARIMA (1,0,3) for KShs/Canadian dollar currency exchange rates. After forecasting, we then compared the forecasted values with the actual data to check the suitability of the ARIMA model. Further, EMD was applied to the exchange rate data and then fitted an ARIMA model to the IMFs. The best model was found to be ARIMA (1,0,1) for the KShs/AE. Dirham, ARIMA (0,0,1) for KShs/Australian dollar and ARIMA (1,0,1) for KShs/Canadian dollar currency exchange rates. The appropriateness of these models was tested using the Ljung-Box test. The forecasting performance of each model was evaluated using the RMSE.
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 | 0.002 | 0.003 |
| 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 | 0.001 |
| 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".