How Simple Can It Get? From Interpretable Equations to Readable Rules for Financial Decision Making
2026-08-10 • Machine Learning
Machine LearningArtificial Intelligence
AI summaryⓘ
The authors focus on making financial prediction models easier for humans, especially regulators, to understand. They start with a simple equation-based model and gradually simplify it into even easier formats like rules and scorecards used in finance. They measure how much accuracy is lost at each step and find that some simplifications keep models effective even if they don’t exactly match the original. They also show that simpler models are generally easier for people to read, but preferences differ based on professional experience. Additionally, the authors provide ways to predict how much simplification might change the model's behavior.
interpretable classifiermodel simplificationpruningscorecardsfinancial regulationrule-based modelsmodel fidelitypredictive performanceexplainable AIranking preservation
Authors
Adia Lumadjeng, Ilker Birbil, Erman Acar
Abstract
In regulated domains such as finance, a model that cannot be explained cannot be deployed, yet many interpretable classifiers defeat their own purpose by producing formulas with dozens of features that no regulator could read. We take the reverse direction. Starting from an interpretable classifier expressed as a single equation over the input features, we progressively simplify it into more readable forms, including a pruned monomial, a directional if--then rule, and the integer scorecards and tallies that finance already deploys. Because the equation is itself the predictive model rather than a post-hoc explanation we can directly quantify what is lost under each simplification. Across four financial datasets, we find that pruning is nearly free and that fidelity can erode faster than predictive performance, allowing simpler rules to remain effective classifiers without faithfully reproducing the original model. A human assessment shows that simplification improves perceived readability, while preferences for different representations vary by professional background. Beyond measuring these losses empirically, we show that some can be anticipated from the original model: we derive a bound on the change caused by pruning and predict how faithfully a rule retaining only the direction of each feature's effect preserves the original ranking.