Behavioural Analytics: Exploring judgments and choices in large data sets

Abstract

The ever-increasing availability of large data-sets that store users’ judgements (such as forecasts and preferences) and choices (such as acquisitions of goods and services) provides a fertile ground for Behavioural Operational Research (BOR). In this paper, we review the streams of Behavioural Decision Research that might be useful for BOR researchers and practitioners to analyse such behavioural data-sets. We then suggest ways that concepts from these streams can be employed in exploring behavioural data-sets for (i) detecting behavioural patterns, (ii) exploiting behavioural findings and (iii) improving judgements and decisions of consumers and citizens. We also illustrate how this taxonomy for behavioural analytics might be utilised in practice, in three real-world studies with behavioural data-sets generated by websites and online user activity.

Keywords:

• Behavioural operational research
• behavioural data mining
• decision analytics

Acknowledgements

The authors wish to thank those at Superbru and Online Skill Ltd. for granting permission to report results obtained using their data. They are also grateful for the valuable feedback of three anonymous referees and the support of the editor.

Notes

No potential conflict of interest was reported by the authors.

Additional information

Funding

This work is based on the research supported in part by the National Research Foundation of South Africa [grant numbers 90782, 105782].