Out-of-sample forecast
An out-of-sample forecast is a model-generated prediction for an observation not included in the data used to fit the model.
Effective Data Analysis
An out-of-sample prediction is a model-generated estimate for an observation not included in the data used to fit the model.
- How it is used
- Supports planning and decisions by estimating outcomes for records whose outcomes are not yet available.
- How deep it goes
- Explains prediction from fitted coefficients and demonstrates held-out evaluation; cautions that real-world applicability needs further testing.
- Examples
- Uses new-house price estimates and rat-sighting predictions, with training-versus-test RMSE and R-squared.
- What you can do after
- Apply it via scikit-learn to generate held-out predictions and compare training and test performance before considering delivery to stakeholders.
Read how Effective Data Analysis explains out-of-sample forecast →
Time Series Forecasting Using Foundation Models
An out-of-sample forecast is a prediction for future observations that were not included in the model input or fitting data.
- How it is used
- Uses future-held-out prediction to demonstrate zero-shot time-series inference with Lag-Llama.
- How deep it goes
- Explains dataset preparation, horizon selection, inference, and interval formatting, but defers formal evaluation metrics.
- Examples
- Uses Walmart weekly sales, four stores, an eight-week horizon, forecast samples, medians, and 95% prediction intervals.
- What you can do after
- Builds future forecasts with Lag-Llama and formats sampled outputs as median predictions with confidence intervals.
Read how Time Series Forecasting Using Foundation Models explains out-of-sample forecast →
Related concepts
- language modelproduced by · A language model is a computational model that represents patterns in linguistic tokens to estimate sequence probabilities and predict or generate language from context.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.