Predicting human decisions with behavioral theories and machine learning

04/15/2019
by   Ori Plonsky, et al.
0

Behavioral decision theories aim to explain human behavior. Can they help predict it? An open tournament for prediction of human choices in fundamental economic decision tasks is presented. The results suggest that integration of certain behavioral theories as features in machine learning systems provides the best predictions. Surprisingly, the most useful theories for prediction build on basic properties of human and animal learning and are very different from mainstream decision theories that focus on deviations from rational choice. Moreover, we find that theoretical features should be based not only on qualitative behavioral insights (e.g. loss aversion), but also on quantitative behavioral foresights generated by functional descriptive models (e.g. Prospect Theory). Our analysis prescribes a recipe for derivation of explainable, useful predictions of human decisions.

READ FULL TEXT
research
09/23/2020

Behavioral Specification Theories: an Algebraic Taxonomy

We develop a taxonomy of different behavioral specification theories and...
research
07/03/2020

PsychFM: Predicting your next gamble

There is a sudden surge to model human behavior due to its vast and dive...
research
05/03/2022

Integration of Behavioral Economic Models to Optimize ML performance and interpretability: a sandbox example

This paper presents a sandbox example of how the integration of models b...
research
07/17/2020

How Flexible is that Functional Form? Quantifying the Restrictiveness of Theories

We propose a new way to quantify the restrictiveness of an economic mode...
research
06/21/2017

The Theory is Predictive, but is it Complete? An Application to Human Perception of Randomness

When we test a theory using data, it is common to focus on correctness: ...
research
08/26/2020

"Improving" prediction of human behavior using behavior modification

The fields of statistics and machine learning design algorithms, models,...
research
10/05/2018

Predicting and Explaining Behavioral Data with Structured Feature Space Decomposition

Modeling human behavioral data is challenging due to its scale, sparsene...

Please sign up or login with your details

Forgot password? Click here to reset