6.7.3 Generate Forecasts

6.7.3.1 Forecasting Task Types
6.7.3.2 Prediction Intervals
6.7.3.3 Prepare Data for a Forecasting Model
6.7.3.4 Train a Forecasting Model
6.7.3.5 Generate Predictions for a Forecasting Model
6.7.3.6 Score a Forecasting Model

Forecasting models generate predictions on timeseries data. Some examples of forecasting include predicting the closing price of a stock, predicting the number of units sold in a day, and predicting the average price of gasoline.

The following tasks use a dataset generated by OCI GenAI using Meta Llama Models. The forecasting use-case is a univariate forecasting model that captures the monthly demand for electricity in San Francisco, California.

To generate your own datasets to create machine learning models in MySQL HeatWave, learn how to Generate Text-Based Content.

Note

Datasets were generated using Meta Llama models. Your use of this Llama model is subject to your Oracle agreements and this Llama license agreement: https://downloads.mysql.com/docs/LLAMA_31_8B_INSTRUCT-license.pdf.