Accuracy Vs. Simplicity: A Complex Trade-Off
51 Pages Posted: 20 Oct 2002
Date Written: August 2002
Abstract
Inductive learning aims at finding general rules that hold true in a database. Targeted learning seeks rules for the prediction of the value of a variable based on the values of others, as in the case of linear or non-parametric regression analysis. Non-targeted learning finds regularities without a specific prediction goal. We model the product of non-targeted learning as rules that state that a certain phenomenon never happens, or that certain conditions necessitate another. For all types of rules, there is a trade-off between the rule's accuracy and its simplicity. Thus rule selection can be viewed as a choice problem, among pairs of degree of accuracy and degree of complexity. However, one cannot in general tell what is the feasible set in the accuracy complexity space. Formally, we show that finding out whether a point belongs to this set is computationally hard. In particular, in the context of linear regression, finding a small set of variables that obtain a certain value of R2 is computationally hard. Computational complexity may explain why a person is not always aware of rules that, if asked, she would find valid. This, in turn, may explain why one can change other people's minds (opinions, beliefs) without providing new information.
Suggested Citation: Suggested Citation
Do you have negative results from your research you’d like to share?
Recommended Papers
-
Limited Attention, Information Disclosure, and Financial Reporting
-
Investor Psychology in Capital Markets: Evidence and Policy Implications
By Kent D. Daniel, David A. Hirshleifer, ...
-
Market Frictions, Price Delay, and the Cross-Section of Expected Returns
By Kewei Hou and Tobias J. Moskowitz
-
Do Investors Overvalue Firms with Bloated Balance Sheets?
By David A. Hirshleifer, Kewei Hou, ...
-
Why Do New Issues and High-Accrual Firms Underperform: The Role of Analysts' Credulity
By Siew Hong Teoh and T.j. Wong
-
Driven to Distraction: Extraneous Events and Underreaction to Earnings News
By David A. Hirshleifer, Sonya S. Lim, ...
-
Industry Information Diffusion and the Lead-Lag Effect in Stock Returns
By Kewei Hou
-
Learning with Information Capacity Constraints
By Lin Peng