Predictive Model Accuracy
Discussions center on the use, reliability, and skepticism surrounding machine learning and statistical models for forecasting future events based on historical data, including time series predictions and methods like regression or neural networks.
Activity Over Time
Top Contributors
Keywords
Sample Comments
Don't we need models to make predictions about the future?
You can't make accurate predictions without some kind of model
What prediction algorithm are you using for this? Not sure if it's mentioned elsewhere on the site
Probably feed it with historical data and see if it can tell what has happened.
Sounds like a "prediction" just like the results you get from training your stock picker on historical data.
A predictor doesnt have to be always right to be a predictor.
Forecast! Time to reach for your linear regression, GBDT or NN.
This is fantastic, thank you. Any chance of adding predictions based on past performance, etc?
Is there a reason you believe the models can accurately predict this sort of thing?
* this is assuming the past continues to be a predictor of the future