Learning to Call: A Field Trial of a Collaborative Bandit Algorithm for Optimizing Call Timing in Mobile Maternal Health

Arpan Dasgupta, Mizhaan Prajit Maniyar, Awadhesh Srivastava, Sanat Kumar, Amrita Mahale, Aparna Hegde, Arun Suggala, Karthikeyan Shanmugam, Milind Tambe, Aparna Taneja
Proceedings of the 10th Machine Learning for Healthcare Conference, PMLR 298, 2025.

Abstract

Mobile health (mHealth) programs utilize automated voice messages to deliver health information, particularly targeting underserved communities, demonstrating the effectiveness of using mobile technology to disseminate crucial health information to these populations, improving health outcomes through increased awareness and behavioral change. India’s Kilkari program delivers vital maternal health information via weekly voice calls to millions of mothers. However, the current random call scheduling often results in missed calls and reduced message delivery. This study presents a field trial of a collaborative bandit algorithm designed to optimize call timing by learning individual mothers’ preferred call times. We deployed the algorithm with  6500 Kilkari participants as a pilot study, comparing its performance to the baseline random calling approach. Our results demonstrate a statistically significant improvement in call pickup rates with the bandit algorithm, indicating its potential to enhance message delivery and impact millions of mothers across India. This research highlights the efficacy of personalized scheduling in mobile health interventions and underscores the potential of machine learning to improve maternal health outreach at scale.

Cite this Paper

BibTeX
@InProceedings{pmlr-v298-dasgupta25a, title = {Learning to Call: A Field Trial of a Collaborative Bandit Algorithm for Optimizing Call Timing in Mobile Maternal Health}, author = {Dasgupta, Arpan and Maniyar, Mizhaan Prajit and Srivastava, Awadhesh and Kumar, Sanat and Mahale, Amrita and Hegde, Aparna and Suggala, Arun and Shanmugam, Karthikeyan and Tambe, Milind and Taneja, Aparna}, booktitle = {Proceedings of the 10th Machine Learning for Healthcare Conference}, year = {2025}, editor = {Agrawal, Monica and Deshpande, Kaivalya and Engelhard, Matthew and Joshi, Shalmali and Tang, Shengpu and Urteaga, Iñigo}, volume = {298}, series = {Proceedings of Machine Learning Research}, month = {15--16 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v298/main/assets/dasgupta25a/dasgupta25a.pdf}, url = {https://proceedings.mlr.press/v298/dasgupta25a.html}, abstract = {Mobile health (mHealth) programs utilize automated voice messages to deliver health information, particularly targeting underserved communities, demonstrating the effectiveness of using mobile technology to disseminate crucial health information to these populations, improving health outcomes through increased awareness and behavioral change. India’s Kilkari program delivers vital maternal health information via weekly voice calls to millions of mothers. However, the current random call scheduling often results in missed calls and reduced message delivery. This study presents a field trial of a collaborative bandit algorithm designed to optimize call timing by learning individual mothers’ preferred call times. We deployed the algorithm with  6500 Kilkari participants as a pilot study, comparing its performance to the baseline random calling approach. Our results demonstrate a statistically significant improvement in call pickup rates with the bandit algorithm, indicating its potential to enhance message delivery and impact millions of mothers across India. This research highlights the efficacy of personalized scheduling in mobile health interventions and underscores the potential of machine learning to improve maternal health outreach at scale.} }
Endnote
%0 Conference Paper %T Learning to Call: A Field Trial of a Collaborative Bandit Algorithm for Optimizing Call Timing in Mobile Maternal Health %A Arpan Dasgupta %A Mizhaan Prajit Maniyar %A Awadhesh Srivastava %A Sanat Kumar %A Amrita Mahale %A Aparna Hegde %A Arun Suggala %A Karthikeyan Shanmugam %A Milind Tambe %A Aparna Taneja %B Proceedings of the 10th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2025 %E Monica Agrawal %E Kaivalya Deshpande %E Matthew Engelhard %E Shalmali Joshi %E Shengpu Tang %E Iñigo Urteaga %F pmlr-v298-dasgupta25a %I PMLR %U https://proceedings.mlr.press/v298/dasgupta25a.html %V 298 %X Mobile health (mHealth) programs utilize automated voice messages to deliver health information, particularly targeting underserved communities, demonstrating the effectiveness of using mobile technology to disseminate crucial health information to these populations, improving health outcomes through increased awareness and behavioral change. India’s Kilkari program delivers vital maternal health information via weekly voice calls to millions of mothers. However, the current random call scheduling often results in missed calls and reduced message delivery. This study presents a field trial of a collaborative bandit algorithm designed to optimize call timing by learning individual mothers’ preferred call times. We deployed the algorithm with  6500 Kilkari participants as a pilot study, comparing its performance to the baseline random calling approach. Our results demonstrate a statistically significant improvement in call pickup rates with the bandit algorithm, indicating its potential to enhance message delivery and impact millions of mothers across India. This research highlights the efficacy of personalized scheduling in mobile health interventions and underscores the potential of machine learning to improve maternal health outreach at scale.
APA
Dasgupta, A., Maniyar, M.P., Srivastava, A., Kumar, S., Mahale, A., Hegde, A., Suggala, A., Shanmugam, K., Tambe, M. & Taneja, A.. (2025). Learning to Call: A Field Trial of a Collaborative Bandit Algorithm for Optimizing Call Timing in Mobile Maternal Health. Proceedings of the 10th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 298 Available from https://proceedings.mlr.press/v298/dasgupta25a.html.

Related Material