Algorithm to process and analyze data from edX courses

Main functions
  • Analysis of general IDBx Program data related to registrants, active participants, and those who pass courses and earn certificates in an aggregated and disaggregated manner.
  • Data analysis which allows you to study the interaction between participants and the various learning resources used in the IDBx Program courses. 
  • Visualizations allow for in-depth knowledge of the data and its transformation into information that is comprehensible to the user in real time.  
  • Generation of program reports for both its management and the purposes of collaboration between key actors.

The IDB’s Inter-American Institute for Social and Economic Development (INDES) has developed a series of Massive Open Online Courses (MOOCs) which are part of the IDBx Program, whose objective is to promote open knowledge projects related to social and economic development in Latin America and the Caribbean. In response to the need for reliable information to manage and improve the decision making of the IDBx Program, INDES launched the IDBx Data Engine data project. 


This system extracts, analyzes, and consolidates the information from IDBx courses into a database contained in the data package generated by technological platform edX where these courses are offered. 


This process consists of two components: 


  1. Automation of the process of extracting, transforming and loading data from the data packet and other sources provided by edX. 

  1. Analysis and creation of indicators that serve as input for visualizations and monitoring charts (dashboards). This last component allows for continuous monitoring of the IDBx Program, through the analysis of previously selected variables and key business indicators.

You can see the source code here:


Knowledge areas
Contribution of