Combating energy theft with analytics

Cemig saves US$420,000 a month by identifying commercial losses related to the misuse of power and technical failures

While fraudulent activity in most industries leads to lost revenue or increased risk exposure, energy theft is different. It’s not just about the revenue lost or the drain on the energy grid. Energy theft can be illegal and hazardous. Tampering with equipment – such as meters, pipes and wires – exposes people to the risk of electric shock, explosion, injury or possibly death.

Before using SAS Enterprise Miner, we could find only 35 percent of fraudsters during the inspection. Now we can detect more than 50 percent.

Iguatinan Monteiro
Planning Engineer

In Brazil, the level of energy theft was a concern for the National Electric Energy Agency (Aneel). It estimates that nontechnical loss has a financial impact of US$1.2 billion a year in the country. If the risk to life and limb won’t thwart thieves, perhaps analytics will.

Utilities provider Cemig (Companhia Energética de Minas Gerais) uses SAS® Analytics to increase accuracy in locating power deviations and technical faults in meters scattered around the metropolitan region of Belo Horizonte, Minas Gerais. Because physical inspection of all energy customers is not practical, analytical prioritization enables Cemig to identify and prioritize candidates.

Since implementing SAS® Enterprise Miner™, Iguatinan Monteiro, Planning Engineer for Cemig, says the company saves about $420,000 a month by detecting energy theft. Cemig uses the technology for statistical modeling, helping analyze data about consumption history, socio-demographic information and geographic potential of each household.

“Before using SAS Enterprise Miner, we could find only 35 percent of fraudsters during the inspection. Now we can find more than 50 percent,” says Monteiro.

After analyzing the data, Cemig uses SAS to generate a score for the household or establishment. The score shows the probability that the location is the site of energy theft.

“When the investigator visits the site, he already knows in advance which installed devices are more likely to have failures and deviations,” explains Monteiro. “We also can identify the consumer units with higher volume offset. These are the ones that cause significant harm to the company and to the end consumer.”

CEMIG logo


Detect and mitigate financial losses related to electricity theft, billing errors and meter failure.


SAS® Enterprise Miner™


  • Detects more than 50 percent of energy fraud cases.
  • Pinpoints energy deviations (nontechnical loss).
  • Identifies technical faults in meters (technical loss).
  • Savings of about $420,000 per month.

About Cemig

Cemig is a major electric utilities provider in Brazil. Cemig accounts for 96 percent of Minas Gerais’ concession area, with more than 7.5 million consumers in 774 municipalities. The company is also a power generator, operating 70 plants with an installed capacity of 7,295 megawatts.

The results illustrated in this article are specific to the particular situations, business models, data input, and computing environments described herein. Each SAS customer’s experience is unique based on business and technical variables and all statements must be considered non-typical. Actual savings, results, and performance characteristics will vary depending on individual customer configurations and conditions. SAS does not guarantee or represent that every customer will achieve similar results. The only warranties for SAS products and services are those that are set forth in the express warranty statements in the written agreement for such products and services. Nothing herein should be construed as constituting an additional warranty. Customers have shared their successes with SAS as part of an agreed-upon contractual exchange or project success summarization following a successful implementation of SAS software. Brand and product names are trademarks of their respective companies.