Streamingbandit: Experimenting with bandit policies

Jules Kruijswijk, Robin van Emden, Petri Parvinen, Maurits Kaptein

Research output: Contribution to journalArticleScientificpeer-review

Abstract

A large number of statistical decision problems in the social sciences and beyond can be framed as a (contextual) multi-armed bandit problem. However, it is notoriously hard to develop and evaluate policies that tackle these types of problems, and to use such policies in applied studies. To address this issue, this paper introduces StreamingBandit, a Python web application for developing and testing bandit policies in field studies. StreamingBandit can sequentially select treatments using (online) policies in real time. Once StreamingBandit is implemented in an applied context, different policies can be tested, altered, nested, and compared. StreamingBandit makes it easy to apply a multitude of bandit policies for sequential allocation in field experiments, and allows for the quick development and re-use of novel policies. In this article, we detail the implementation logic of StreamingBandit and provide several examples of its use.

Original languageEnglish
Pages (from-to)1-47
Number of pages47
JournalJOURNAL OF STATISTICAL SOFTWARE
Volume94
DOIs
Publication statusPublished - 2020
MoE publication typeA1 Journal article-refereed

Keywords

  • Data streams
  • Multi-armed bandit
  • Python
  • Sequential decision-making
  • Sequential experimentation

Fingerprint Dive into the research topics of 'Streamingbandit: Experimenting with bandit policies'. Together they form a unique fingerprint.

Cite this