ABSTRACT In the normal course of business, international development institutions investing in development projects generate thousands of project-related documents summarising and analysing each aspect of their policymaking processes and policy lifecycles from design and financing through implementation performance and ultimately project/policy outputs, outcomes and effectiveness-related data. Moreover, institutions’ internal processes for quality assurance, monitoring and results measurement systems generate quantitative and qualitative primary and secondary data that can be employed to extract insights about lessons learned, internal decision-making processes, business model changes and project and portfolio performance. Resource and time constraints, however, result in the underutilisation of these valuable data sources for knowledge management, planning, evaluation and analysis. Specifically, qualitative insights housed in project documents remain largely inaccessible and cannot be employed systematically in combination with other quantitative data, in a unified framework. This article explores how machine learning can accelerate knowledge generation and management and aid results-based decision-making in line with development institutions’ existing development effectiveness frameworks through two main channels. The first leverages project documentation for historical portfolio systematisation to extract key strategic topics as well as lessons learned through the application of techniques such as text mining and topic modelling. The second proposes an agency-based system for predictive analytics, which analyses current and historical data to make predictions about future outcomes or trends to strengthen data-driven decision-making.
Read full abstract