Identifying Fraud & Collusion in International Development Projects

Fellows: Emily Grace, Ankit Rai, Elissa Redmiles
Data Science Mentor(s): Kristin Yvonne Rozier
Project Manager: Alan Fritzler
Project Partner: World Bank Group

Every year, the World Bank Group lends over $30 billion for aid and development to more than 140 countries. However, some analysts estimate that developing countries risk losing billions of dollars each year as a result of fraud and corruption. Misappropriation of funds is most likely to occur at the contract bidding and awarding stage, when bribes, collusion, and other practices can divert money away from projects. The Integrity (INT) Vice Presidency of the World Bank Group responds to allegations and investigates cases of corruption while increasingly using data to locate potentially fraudulent behavior and prevent it.

In 2014, DSSG cooperated with the Integrity Vice Presidency in organizing and analyzing their international contract bidding data to identify suspicious patterns or connections that may indicate fraud or corruption impacting Bank-financed projects. Our 2015 project built upon that work, applying more advanced and specific data science methods to produce actionable evidence useful for INT’s investigative and preventive work. The project relied on global data, apply analytics to identify common bidding patterns, and developed tools to help fraud prevention, detection, and investigation.

You can read about our work in detail here.