On the Unknowable Limits to Prediction
This provides a framework for advancing computational research by clarifying how prediction accuracy can asymptotically improve, though it is incremental in refining existing error decomposition concepts.
The paper tackles the problem of distinguishing between truly irreducible prediction error and error that can be reduced through better data and algorithms, demonstrating that many 'unpredictable' outcomes can become more tractable with iterative improvements.
We propose a rigorous decomposition of predictive error, highlighting that not all 'irreducible' error is genuinely immutable. Many domains stand to benefit from iterative enhancements in measurement, construct validity, and modeling. Our approach demonstrates how apparently 'unpredictable' outcomes can become more tractable with improved data (across both target and features) and refined algorithms. By distinguishing aleatoric from epistemic error, we delineate how accuracy may asymptotically improve--though inherent stochasticity may remain--and offer a robust framework for advancing computational research.