Advancing data reporting and analytics in off-grid solar

Over 1 billion people lack access to electricity, and off-grid solutions need investment. DrivenData worked with The World Bank to analyze repayment data across dozens of pay-as-you-go (PAYG) off-grid solar energy companies and build out key performance indicators for PAYG portfolios.

YouTube video: Why adopt GOGLA - Lighting Global KPIs? A business case shared by Solaris Offgrid

The organization¶

As part of The World Bank’s efforts to combat energy poverty around the globe, it works to foster private sector investment in market-driven solutions. The World Bank’s engagement in the energy sector is designed to help secure the affordable, reliable, and sustainable energy supply needed to end extreme poverty and promote shared prosperity. Its strategy mirrors the objectives of the Sustainable Energy for All Initiative and the Sustainable Development Goal (SDG) on energy, SDG7: achieving universal access, accelerating improvements in energy efficiency, and doubling the global share of renewable energy by 2030.

The challenge¶

Around 1.1 billion people currently lack access to electricity. In recent years, the emergence of cheaper solar energy options, and pay-as-you-go (PAYG) business models that make these options affordable, has provided more people with greater access to clean energy than ever before.

However, many of the distributed energy service companies (DESCOs) providing PAYG off-grid solar products need significantly more capital investment in order to realize their plans for customer expansion and product development. This is a sector with high perceived risk, a weak pipeline, and an unfamiliar asset class, which means that investors have been slow to provide capital to the sector. Meanwhile, companies need to spend existing time and resources operating their business, while there are limited industry standards to help measure and report their performance and limited industry data available to help inform the most effective operating decisions.

The approach¶

Since 2016, DrivenData has worked on multiple projects in off-grid energy, delivering data-driven insight to companies, policymakers, and industry stakeholders.

The World Bank worked first with The Impact Lab and then with DrivenData to develop a sector-wide KPI framework for measuring operational and business performance of energy service providers. These indicators were defined based on input from companies, investors, and funders, and with feedback from testing on company data. The goal of the framework was to develop a first set of industry standards and tools available to off-grid companies, helping to facilitate investment assessments and promote stronger operational performance in the PAYG sector.

Furthermore, The World Bank wanted to promote insights across the industry by bringing advanced data science approaches to the data from real companies. The PAYG off-grid sector generates data from both arms of its business: selling energy devices and extending credit. Insights from these data sources—like who is most likely to pay on time, when devices are likely to require maintenance, and how to design customer agreements to increase the likelihood of repayment—drive improved outcomes for both customers and companies.

Making sense of data at this scale can be challenging, but it is increasingly important to companies that need to understand their sustainability and profitability. This kind of analysis is also a key component to unlocking investment in off-grid solar companies. Using this context, DrivenData and The World Bank partnered with Angaza to identify ways to apply advanced data science approaches for the benefit of all. The primary objective: evaluate differences across contract design decisions—like the time customers have to repay, their required downpayment, and the frequency of payments—and model the impact of these decisions on repayment behaviors. Since Angaza is a software provider for many DESCOs, by aggregating and anonymizing data from participating clients, we were able to produce a detailed view of cross-cutting industry trends.

The outcome¶

The GOGLA - Lighting Global KPI framework was published as a resource for PAYG off-grid solar companies and investors. The latest version of the KPI Technical Guide, including indicator definitions, commentary, illustrations, and open source code for calculation, is available through the GOGLA website.

The results of the industry trends analysis were co-presented with Angaza in January 2018 at the Global Off-grid Solar Forum in Hong Kong.

Resources:

The results of the initial modeling effort emphasized trade-offs in influencing on-time repayment; for instance, agents were helpful touch points for encouraging timely payment, while remote mobile payments provide more scalable economics on an ongoing basis. It also confirmed that more frequent payments were associated with more timely repayment, all else equal, supporting the most common industry practice of weekly payments.

Beyond the immediate analysis, the partnership with Angaza highlighted the potential for public-private partnerships in PAYG solar. Often in this industry, the impact and the business cases align. Partnering on data-sharing can improve the outcomes that everyone cares about.

Image from Industry Trends Analysis highlighting regional difference in price per day charged for solar home systems; shared at the Global Off-Grid Forum and Expo 2018 in Hong Kong

Our real-world impact

All projects

Partners: Max Planck Institute for Evolutionary Anthropology, Arcus Foundation, WILDLABS

Automating wildlife identification for research and conservation

Detected wildlife in images and videos—automatically and at scale—by building the winning algorithm from a DrivenData competition into an open source python package and a web application running models in the cloud.

Partners: Private sector, social sector

Building LLM solutions

Built solutions using LLMs for multiple real-world applications, across tasks including semantic search, summarization, named entity recognition, and multimodal analysis. Work has spanned research on state-of-the-art models tuned for specific use cases to production ready retrieval-augmented AI applications.

Partners: The World Bank, The Conflict and Environment Observatory

Identifying crop types using satellite imagery in Yemen

Used satellite imagery to identify crop extent, crop types and climate risks to agriculture in Yemen, informing World Bank development programs in the country after years of civil war.

Partners: IDEO.org

Illuminating mobile money experiences in Tanzania

Analyzed millions of mobile money records to uncover patterns in behavior, and then combined these insights with human-centered design to shape new approaches to delivering mobile money to low-income populations in Tanzania.

Partners: Insecurity Insight, Physicians for Human Rights

Tracking attacks on health care in Ukraine

Built a real-time, interactive map to visualize attacks on the Ukrainian health care system since the Russian invasion began in February of 2022. The map will support partner efforts to provide aid, hold aggressors accountable in court, and increase public awareness.

Partners: CABI Plantwise

Mining chat messages with plant doctors using language models

Automated recognition of agricultural entities (such as crops, pests, diseases, and chemicals) in WhatsApp and Telegram messages among plant doctors, enabling new ways to surface emerging trends and improve science-based guidance for smallholder farmers.

Partners: Data science company foundation

Matching students with schools where they are likely to succeed

Used machine learning to match students with higher education programs where they are more likely to get in and graduate based on their unique profile, with a focus on backgrounds traditionally less likely to attend college or apply to more competitive programs.