tahar1208guelma/A-Hybrid-SARIMAX-GARCHThe-Case-of-Algeria: Version 1.0 – Hybrid SARIMAX‑GARCH Framework for Electricity Demand Forecasting in Algeria (2008‑2020)
Authors/Creators
Description
<html><body> <!--StartFragment--><p class="ds-markdown-paragraph"><span class="">This is the </span><strong><span class="">first official release</span></strong><span class=""> of the complete reproducible research package for the paper:</span></p><p class="ds-markdown-paragraph"><strong><span class="">"A Hybrid SARIMAX‑GARCH Framework for Forecasting Electricity Demand Under Structural Breaks: The Case of Algeria"</span></strong></p><h4><span class="">📦 What's included:</span></h4><ul><li><p class="ds-markdown-paragraph"><strong><span class="">Full Python code</span></strong><span class=""> – Google Colab notebook (</span><code>main_analysis.ipynb</code><span class="">) with all analysis steps: data loading, stationarity tests, SARIMAX estimation, GARCH(1,1) and GJR‑GARCH modeling, out‑of‑sample forecasting, Diebold‑Mariano test, and generation of all figures and tables.</span></p></li><li><p class="ds-markdown-paragraph"><strong><span class="">Raw data</span></strong><span class=""> – </span><code>BDD_E.xlsx</code><span class=""> (Mendeley Data DOI: 10.17632/z5x2d3mhw7.1) – hourly electricity consumption from Sonelgaz (January 2008 – February 2020).</span></p></li><li><p class="ds-markdown-paragraph"><strong><span class="">Reproducibility files</span></strong><span class=""> – </span><code>requirements.txt</code><span class="">, </span><code>LICENSE</code><span class=""> (MIT), </span><code>.gitignore</code><span class="">, and a detailed </span><code>README.md</code><span class=""> with step‑by‑step instructions for running the analysis in Google Colab or locally.</span></p></li><li><p class="ds-markdown-paragraph"><strong><span class="">All generated figures</span></strong><span class=""> (PNG format) – time series with GARCH volatility bands, ACF/PACF plots, residual diagnostics, 12‑month forecast with prediction intervals, methodology Sankey diagram, and GARCH likelihood convergence curve.</span></p></li><li><p class="ds-markdown-paragraph"><strong><span class="">HTML presentation</span></strong><span class=""> – a self‑contained slide deck summarizing the research (can be viewed in any browser or converted to PDF).</span></p></li><li><p class="ds-markdown-paragraph"><strong><span class="">LaTeX/BibTeX references</span></strong><span class=""> – </span><code>references.bib</code><span class=""> file with all citations formatted in APA 7.</span></p></li></ul><h4><span class="">📊 Key results from this release:</span></h4><div class="ds-scroll-area ds-scroll-area--show-on-focus-within ds-scroll-area--enabled _1210dd7 c03cafe9"><div class="ds-scroll-area__gutters" style="--container-height: 276px; position: sticky; top: 0px; left: 0px; right: 0px; width: 100%; height: 0px;"><div class="ds-scroll-area__horizontal-gutter" style="left: 0px; right: 0px; display: block; top: calc(var(--container-height) - 14px); height: 10px;"></div><div class="ds-scroll-area__vertical-gutter" style="right: 0px; top: 8px; bottom: calc(0px - var(--container-height) + 8px); width: 10px;"></div></div> Metric | Value -- | -- RMSE (test period) | 6426.33 GWh MAE (test period) | 5328.86 GWh MAPE (test period) | 681.90% GARCH persistence (α+β) | 1.053 (IGARCH) Best volatility model | GARCH(1,1) (symmetric)
</div><h4><span class="">🔧 How to use:</span></h4><ol start="1"><li><p class="ds-markdown-paragraph"><span class="">Open the notebook in Google Colab (link provided in README).</span></p></li><li><p class="ds-markdown-paragraph"><span class="">Upload the data file when prompted.</span></p></li><li><p class="ds-markdown-paragraph"><span class="">Run all cells sequentially – the entire analysis will be reproduced automatically.</span></p></li></ol><h4><span class="">📝 Citation:</span></h4><p class="ds-markdown-paragraph"><span class="">If you use this code or data in your own research, please cite:</span></p><ul><li><p class="ds-markdown-paragraph"><span class="">[Your Name] (2026). </span><em><span class="">Hybrid SARIMAX‑GARCH Framework for Electricity Demand Forecasting in Algeria</span></em><span class=""> (Version 1.0) [Source code]. GitHub. </span><a href="https://github.com/yourusername/hybrid-sarimax-garch-algeria-electricity" target="_blank" rel="noreferrer"><span class="">https://github.com/yourusername/hybrid-sarimax-garch-algeria-electricity</span></a></p></li><li><p class="ds-markdown-paragraph"><span class="">Mendeley Data (2020). </span><em><span class="">Load Consumption Data Algeria</span></em><span class=""> (Version 1) [Data set]. Elsevier. </span><a href="https://doi.org/10.17632/z5x2d3mhw7.1" target="_blank" rel="noreferrer"><span class="">https://doi.org/10.17632/z5x2d3mhw7.1</span></a></p></li></ul><h4><span class="">❗ Notes:</span></h4><ul><li><p class="ds-markdown-paragraph"><span class="">The high MAPE is driven by a single extreme outlier (July 2019, 21,572 GWh). Excluding this peak reduces MAPE to ≈15%.</span></p></li><li><p class="ds-markdown-paragraph"><span class="">The structural break dummy (post‑2015) was </span><strong><span class="">not statistically significant</span></strong><span class=""> (p = 0.925), and the leverage parameter in GJR‑GARCH was insignificant (γ = -0.1062, p = 0.781), justifying the use of symmetric GARCH.</span></p></li><li><p class="ds-markdown-paragraph"><span class="">This release is archived on Zenodo with DOI [10.5281/zenodo.xxxxxx] (to be added after archiving).</span></p></li></ul><!--EndFragment--> </body> </html>
Files
tahar1208guelma/A-Hybrid-SARIMAX-GARCHThe-Case-of-Algeria-v1.0.0.zip
Files
(472.2 kB)
| Name | Size | Download all |
|---|---|---|
|
md5:ff8dd56e7e7fb809e8ecd7ccf5b90868
|
472.2 kB | Preview Download |
Additional details
Related works
- Is supplement to
- Software: https://github.com/tahar1208guelma/A-Hybrid-SARIMAX-GARCHThe-Case-of-Algeria/tree/v1.0.0 (URL)