Improving delivery of safe water to African communities with
summary
Data analysis claims falling water delivery is driven not by lowered per‑user consumption but by losing users: 181 issued cards drop to 77 inactive and 45 retain funds but stop transacting, and daily liters fall as lost cards rise. Work uses transaction logs, weather and socio‑economic data in Jupiter notebooks, Spark and pandas on a Blum miix stack, and produces alerts and dashboard prototypes; experiments (distribute replacement cards, change replacement cost) are proposed and the leak‑fixing recommendation shows measurable reversal potential.
AI-written summary · about
chapters (8)
- 0:00Water Mission intro
- 4:22Living Water kiosks
- 7:13Data analysis context
- 10:26Konda water trends
- 15:44Inactive smart cards
- 20:22Card loss root cause
- 26:30Kiosk usage tips
- 29:23Q&A
related talks
26mFrom Data to Decision: Monitoring and Improving Water Networks using AI/ML
20mUsing Data to Protect Traditional Lifeways
22mSustainable Analytics
29mLet’s Talk About Data Strategy
26mData Science is Key to Achieving Energy Access in Africa
20mUsing R, the Tidyverse, H2O, and Shiny to reduce employee attrition
25mData science and machine learning in wastewater intelligence 🌳
40mDesign for Data