AI-driven diet planning applications for optimizing food security: a case study of low-income households in Chitungwiza, Zimbabwe

Abstract

In many low-income communities, especially in urban areas like Chitungwiza, Zimbabwe, food insecurity is still a major problem. The possibility of AI-driven diet planning apps as cutting-edge instruments for maximising household food security is investigated in this study. These apps can create customized meal programs that optimize both cost and nutritional sufficiency by utilising machine learning algorithms to assess dietary requirements, local food availability, and financial limitations. The study examined how AI-based meal planning might promote sustainable consumption habits and increase resilience to food scarcity by using a case study methodology to examine the experiences of low-income households in Chitungwiza. Focus groups, interviews, and household surveys were used to gather information. Results suggest that AI-driven solutions can improve food usage efficiency, decrease waste, and provide households with practical dietary advice, all of which can support more comprehensive food security policies in environments with limited resources. Incorporating AI into community-level nutrition planning presents a viable strategy to combat food insecurity in Zimbabwe and other Sub-Saharan African contexts.