Enregistré dans:
Détails bibliographiques
Auteurs principaux: Seow, Roderick, Zhao, Yunfan, Wood, Duncan, Tambe, Milind, Gonzalez, Cleotilde
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2408.16147
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909303515906048
author Seow, Roderick
Zhao, Yunfan
Wood, Duncan
Tambe, Milind
Gonzalez, Cleotilde
author_facet Seow, Roderick
Zhao, Yunfan
Wood, Duncan
Tambe, Milind
Gonzalez, Cleotilde
contents For public health programs with limited resources, the ability to predict how behaviors change over time and in response to interventions is crucial for deciding when and to whom interventions should be allocated. Using data from a real-world maternal health program, we demonstrate how a cognitive model based on Instance-Based Learning (IBL) Theory can augment existing purely computational approaches. Our findings show that, compared to general time-series forecasters (e.g., LSTMs), IBL models, which reflect human decision-making processes, better predict the dynamics of individuals' states. Additionally, IBL provides estimates of the volatility in individuals' states and their sensitivity to interventions, which can improve the efficiency of training of other time series models.
format Preprint
id arxiv_https___arxiv_org_abs_2408_16147
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Improving the Prediction of Individual Engagement in Recommendations Using Cognitive Models
Seow, Roderick
Zhao, Yunfan
Wood, Duncan
Tambe, Milind
Gonzalez, Cleotilde
Machine Learning
Multiagent Systems
For public health programs with limited resources, the ability to predict how behaviors change over time and in response to interventions is crucial for deciding when and to whom interventions should be allocated. Using data from a real-world maternal health program, we demonstrate how a cognitive model based on Instance-Based Learning (IBL) Theory can augment existing purely computational approaches. Our findings show that, compared to general time-series forecasters (e.g., LSTMs), IBL models, which reflect human decision-making processes, better predict the dynamics of individuals' states. Additionally, IBL provides estimates of the volatility in individuals' states and their sensitivity to interventions, which can improve the efficiency of training of other time series models.
title Improving the Prediction of Individual Engagement in Recommendations Using Cognitive Models
topic Machine Learning
Multiagent Systems
url https://arxiv.org/abs/2408.16147