Millicent Ochieng
Millicent Ochieng has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Jacki O'NEill
Microsoft Research Africa, Nairobi, Kenya
3 shared publications - Elizabeth Ankrah
University of California, Irvine, Irvine, CA, USA
2 shared publications - Mercy Muchai
Microsoft Research Lab Africa, Nairobi, Kenya
2 shared publications - Najeeb Gambo Abdulhamid
Microsoft Research Lab, Nairobi, Kenya, Microsoft, NAIROBI, Nairobi, Kenya
2 shared publications - Samuel Chege Maina
Microsoft Research Lab Africa, Nairobi, Kenya
2 shared publications - Stephanie Nyairo
Microsoft Research Lab Africa, Nairobi, Kenya
2 shared publications
Latest Publications
- Open Access
- 4 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 415-418
Advancing Sustainable Agricultural Practices in Africa with AI: Interdisciplinary Approaches to Inclusivity and Resilience
- 4 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 415-418
Open AccessAdvancing Sustainable Agricultural Practices in Africa with AI: Interdisciplinary Approaches to Inclusivity and Resilience
- Open Access
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-19
Social by Nature: How Socio-tecture Shapes the Work of SMBs and Considerations for Reimagining Collaborative Human-AI Systems
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-19
Open AccessSocial by Nature: How Socio-tecture Shapes the Work of SMBs and Considerations for Reimagining Collaborative Human-AI Systems
- Open Access
- 6 December 2023
- Published by Association for Computing Machinery (ACM) in ACM Journal on Computing and Sustainable Societies
- Vol. 1 (2) , 1-23
Evaluation of Dependency Structure for Multivariate Weather Predictors Using Copulas
In the Global South, the effects of climate change have resulted in more frequent and severe weather events such as droughts, floods, and storms, leading to crop failures, food insecurity, and job loss. These effects are expected to increase in intensity in the future, further disadvantaging already marginalized communities and exacerbating existing inequalities. Hence, the need for prevention and adaptation is urgent, but accurate weather forecasting remains challenging, despite advances in machine learning and numerical modeling, due to complex interaction of atmospheric and oceanic variables. This research aims to explore the potential of vine copulas in explaining complex relationships of different weather variables in three African locations. Copulas separate marginal distributions from the dependency structure, offering a flexible way to model dependence between random variables for improved risk assessments and simulations. Vine copulas are based on a variety of bivariate copulas, including Gaussian, Student’s t , Clayton, Gumbel, and Frank copulas, and they are effective in high-dimensional problems and offer a hierarchy of trees to express conditional dependence. In addition, we propose how this framework can be applied within the subseasonal forecasting models to enhance the prediction of different weather events or variables.
- 6 December 2023
- Published by Association for Computing Machinery (ACM) in ACM Journal on Computing and Sustainable Societies
- Vol. 1 (2) , 1-23
Open AccessEvaluation of Dependency Structure for Multivariate Weather Predictors Using Copulas
In the Global South, the effects of climate change have resulted in more frequent and severe weather events such as droughts, floods, and storms, leading to crop failures, food insecurity, and job loss. These effects are expected to increase in intensity in the future, further disadvantaging already marginalized communities and exacerbating existing inequalities. Hence, the need for prevention and adaptation is urgent, but accurate weather forecasting remains challenging, despite advances in machine learning and numerical modeling, due to complex interaction of atmospheric and oceanic variables. This research aims to explore the potential of vine copulas in explaining complex relationships of different weather variables in three African locations. Copulas separate marginal distributions from the dependency structure, offering a flexible way to model dependence between random variables for improved risk assessments and simulations. Vine copulas are based on a variety of bivariate copulas, including Gaussian, Student’s t , Clayton, Gumbel, and Frank copulas, and they are effective in high-dimensional problems and offer a hierarchy of trees to express conditional dependence. In addition, we propose how this framework can be applied within the subseasonal forecasting models to enhance the prediction of different weather events or variables.
- Open Access
- 27 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 64-70
Can Large Language Models Support Medical Facilitation Work? A Speculative Analysis
Mobile messaging apps and SMS-based tools have been deployed to extend healthcare services beyond the clinic; peer support chat groups, consisting of patients and healthcare providers, can improve medication adherence. However, moderation can be burdensome for busy healthcare professionals who must respond to patients, provide accurate and timely information, and engage and build community among patients. In this paper, taking an ethnographic approach, we examine the moderation of chat groups for young people living with HIV in Kenya. We describe the roles and responsibilities of the moderator while striving to engage and build community among the participants and manage the group chat, highlighting the challenges they face. Grounded in the moderators' work, we explore how an LLM-enabled copilot could help or hinder group facilitation. In doing so, we contribute to discussions about the potential of Artificial Intelligence in supporting healthcare professionals.
- 27 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 64-70
Open AccessCan Large Language Models Support Medical Facilitation Work? A Speculative Analysis
Mobile messaging apps and SMS-based tools have been deployed to extend healthcare services beyond the clinic; peer support chat groups, consisting of patients and healthcare providers, can improve medication adherence. However, moderation can be burdensome for busy healthcare professionals who must respond to patients, provide accurate and timely information, and engage and build community among patients. In this paper, taking an ethnographic approach, we examine the moderation of chat groups for young people living with HIV in Kenya. We describe the roles and responsibilities of the moderator while striving to engage and build community among the participants and manage the group chat, highlighting the challenges they face. Grounded in the moderators' work, we explore how an LLM-enabled copilot could help or hinder group facilitation. In doing so, we contribute to discussions about the potential of Artificial Intelligence in supporting healthcare professionals.