FORECASTING ELECTRICITY PRICES IN CANADA: A COMPARATIVE ANALYSIS OF ARIMA, LSTM, AND XGBOOST MODELS FOR FINANCIAL DECISION-MAKING
Bibliographic record
Abstract
Abstract Forecasting electricity prices is important for smart decisions in the energy field. This includes investors, utility companies, and students studying energy finance. In Canada, more provinces are gaining control over their power systems and using more renewable energy. These changes have made electricity prices more unstable and harder to predict. This study compares how well three models can forecast prices: Autoregressive Integrated Moving Average (ARIMA), Long Short-Term Memory (LSTM) networks, and Extreme Gradient Boosting (XGBoost). The models are tested using hourly electricity price data from Alberta, taken from the Alberta Electric System Operator (AESO) from 2015 to 2023. To measure how accurate the models are, we use three common metrics: Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE). The results show that ARIMA works fairly well with steady data but performs poorly when prices change quickly. LSTM does better by recognizing patterns over time. XGBoost gives the best results overall, especially when handling complex and changing price trends. Although none of the models is perfect, machine learning models like XGBoost seem to be more reliable. These findings can help guide future research and support better forecasting in Canada’s electricity market.
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 | 0.003 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.002 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".