Build and Deploy a Forecaster
The Allora Forecaster is designed to run a model that predicts how accurate inferers are at arbitrary tasks. Any forecaster can be augmented using proprietary data sources, which likely overlap with the data used by inference models. A boilerplate forecaster (opens in a new tab) has been provided that has demonstrated ability for arbitrary topics.
Forecaster Components Overview
| Component | Purpose | Key Functions |
|---|---|---|
| Data Indexing | Retrieves necessary data from the blockchain using the Postgres indexer. | Utilizes the extract folder for querying data from Postgres and making it accessible to the forecaster. |
| Modeling | Core functionality for model selection and training. | Supports different machine learning algorithms like LightGBM and XGBoost. |
| Prediction Engine | Runs selected models on historical data to generate future predictions. | Ingests time-series data and outputs forecast values based on the chosen model. |
| Model Plots | Visualizes model performance and forecast accuracy. | Generates plots such as Prediction vs Actual, Residuals, and Forecast Horizon for intuitive evaluation. |
| Performance Metrics | Measures the accuracy and effectiveness of model predictions. | Key metrics include MAE (Mean Absolute Error), RMSE (Root Mean Squared Error), R2 Score, Mean Absolute Percentage Error, Median Absolute Percentage Error |
| Scoring Mechanism | Assigns scores based on model performance compared to other participants. | Determines which forecasts contribute to the Allora Network’s final consensus based on accuracy and uniqueness. |