Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

Real Time Utility Bill Analytics with Machine Learning:A Mobile Solution For Escom Prepaid Users in Malawi

Domain:

digital infrastructureenvironment and energy

Record type:

softwareproject
Creator:
ChiCha
Editor:
Cha
Publisher:
Zenodo
Host:avatar

This project presents the development of a mobile application, "RealTime Utility Bill Analytics with Machine Learning," designed to enhance electricity management for prepaid users of the Electricity Supply Corporation of Malawi (ESCOM). In Malawi, where prepaid systems dominate and challenges like inaccessible billing, unpredictable usage, and delayed infrastructure responses persist, this app provides a unified platform for real-time bill viewing, payment processing, consumption analytics, budgeting, and issue reporting.
Key features include: seamless integration with ESCOM's API for retrieving current and historical bills; machine learning-driven predictions of future usage patterns to aid informed decision-making; proactive notifications for low electricity levels (e.g., below 20 kWh) and personalized energy-saving tips; a geolocation-enhanced module for reporting infrastructure issues like faulty meters or outages; and budgeting tools with alerts (e.g., at 80% of a 150 kWh monthly limit). Built using Flutter for cross-platform compatibility (Android/iOS), the app employs a green-themed interface and plans for SMS/USSD support to ensure accessibility in low-tech rural areas.
A literature review highlights gaps in existing utility apps, such as limited predictive analytics and integration, which this solution addresses to potentially reduce consumption by 5-10% through user awareness. The project underscores the role of mobile technology in promoting energy efficiency and financial inclusion in developing regions.

Visit

doi.org

Tasks

language modeling

Tags

electricity managementmachine learningmobile appEscomprepaid utilitiesenergy analyticsMalawiFlutterUSSD

Licenses

info:eu-repo/semantics/openAccessCreative Commons Attribution 4.0 Internationalhttps://creativecommons.org/licenses/by/4.0/legalcode

Similar

Real-Time Predictive Analytics in Multi-Phase Flow Metering for Offshore Pipelines: A Machine Learning ApproachIoV distributed architecture for real-time traffic data analyticsOtutu11/Real-Time-Disaster-Impact-Analytics-PlatformOkuhleMaduna/A-Machine-Learning-Solution-for-Data-Driven-Crime-Analytics-in-South-AfricaCharacteristics of first-time family planning users and methods used at mobile clinics in rural MalawiHarnessing Deep Learning for Real-Time Water Quality Assessment: A Sustainable Solution

Real-Time Predictive Analytics in Multi-Phase Flow Metering for Offshore Pipelines: A Machine Learning Approach

This research investigates the deployment of real-time predictive analytics in multi-phase flow mete

IoV distributed architecture for real-time traffic data analytics

International audience In this paper, we present necessary premises for the deploymen

Otutu11/Real-Time-Disaster-Impact-Analytics-Platform

This project simulates a real-time disaster impact analytics platform, using synthetic geospatial da

OkuhleMaduna/A-Machine-Learning-Solution-for-Data-Driven-Crime-Analytics-in-South-Africa

South Africa faces persistent and diverse crime challenges that affect citizens, businesses, and cit

Characteristics of first-time family planning users and methods used at mobile clinics in rural Malawi

Setting: Malawi committed to increase modern contraceptive prevalence rate to 6

Harnessing Deep Learning for Real-Time Water Quality Assessment: A Sustainable Solution

International audience This study presents an innovative approach utilizing artificia