Dukawalla: Voice Interfaces for Small Businesses in Africa

2025-05-08

AI Summary

African small and medium-sized businesses (SMBs) widely lack data-driven decision-making capabilities, primarily due to the misalignment of existing analytical tools with their mobile-first, socially embedded, and low-digital-literacy operational contexts. To address this, we propose the first voice-interaction business intelligence system specifically designed for African SMBs. Our approach integrates lightweight fine-tuned generative AI, multi-turn dialogue management, a localized business knowledge graph, and robust automatic speech recognition (ASR), enabling an end-to-end pipeline from natural-language voice input to real-time, actionable business insights. The system requires no user training, substantially lowering technical adoption barriers. Deployed in Nairobi, it improved user data query efficiency by 3.2×; 87% of shop owners independently performed sales analysis and inventory decisions. These results demonstrate the system’s effectiveness and scalability in resource-constrained environments.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Natural Language Processing: Conversational AI/Dialog Systems
• Humans and AI: AI for Accessibility

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Small and medium sized businesses often struggle with data driven decision making do to a lack of advanced analytics tools, especially in African countries where they make up a majority of the workforce. Though many tools exist they are not designed to fit into the ways of working of SMB workers who are mobile first, have limited time to learn new workflows, and for whom social and business are tightly coupled. To address this, the Dukawalla prototype was created. This intelligent assistant bridges the gap between raw business data, and actionable insights by leveraging voice interaction and the power of generative AI. Dukawalla provides an intuitive way for business owners to interact with their data, aiding in informed decision making. This paper examines Dukawalla's deployment across SMBs in Nairobi, focusing on their experiences using this voice based assistant to streamline data collection and provide business insights

Problem

• Addresses lack of analytics tools for African SMBs
• Simplifies data interaction via voice for mobile-first users
• Bridges raw data and insights with generative AI

Innovation

• Voice interaction for intuitive data access
• Generative AI to provide actionable insights
• Mobile-first design for African SMBs