Revenue Intelligence® for NonTechnical Losses (NTL) is an extremely customizable, modular solution with an intuitive user interface that is COMPLETELY CONFIGURABLE AND PARAMETERIZABLE according to business needs.
A number of key business processes fundemental to all utility customers, are supported by Revenue Intelligence® NTL, through creation of various use cases such as:
- Prioritization of field inspections based on fraud probability and/or financial impact;
- Identification of business process inefficiencies
- technological (data gaps between measurement and collection systems),
- operational (monitoring underperforming field inspection teams),
- administrative (time-consuming audit processes resulting in revenue losses);
- Optimization of meter replacement initiatives;
- Improvement of of field teams productivity based on geographic selection;
- Customer behavior analysis;
- KPI monitoring;
- Support for network investment decisions (e.g., smart meters) focusing on short-term, high investment return oppertunities;
- Enrichment of revenue assurance process using machine learning.
Revenue Intelligence® for NonTechnical Losses (NTL) ) is seperated into 7 modules / apps, where the implementation effort is only subject to the requirements OF THE APPLICATIONS NEEDED:
gathers together a comprehensive set of details for each customer, visible in unison on a single screen, empowering the business user to make decisions unique to the individual situaiton. Detailed search capabilities are also provided, based on the information feed provided by the database.
Interfaces with Google Maps API, providing a comprehensive set of User Interface tools and allowing business users to single out inpsection targets directly. Field inspections can be categorized according to 3 main criteria:
- Financial Impact
- Geographical Location
Additional filter options help to refine inspection targets in order to prioritize high-risk, high-impact combinations, therefore further increasing productivity.
Allows business users to monitor the execution of key processes through comparison with KPIs, such as: number of field inspections performed, hit rate and productivity, matching the results achieved with the annual objectives of the company.
Display options also include export to Excel or send by email.
Makes use of a series of predefined sets of reports created by Choice, based on market experience, with additional options to modify or build new reports using dimensions and KPIs to monitor progression. Predefined options include:
- Optimal number of inspections reporting
- True financial return on inspection analysis
- Inspection Team Monitoring
- Rule/Pattern effectiveness monitoring
Create your own fraud patterns by leveraging your team’s experience. For companies with many subsidiaries or decentralized operations, this app empowers local teams to use make use of insider knowledge particular to each region and customer behavior.
The User Interface is very intuitive, allowing drag-and-drop mechanism to create business rules and simulate expected result effectivness.
The simulation option forecasts the expected effectiveness of a given set of results, as well as expected recovered energy and overall productivity.
Takes full advantage of results from other algorithms or Machine Learning initiatives in Revenue Intelligence®. This information can then be combined with the results coming from the Pattern Detection app (among others) in order to complement any previously existing company initiatives.
A powerful Revenue Intelligence® NTL platform app for geographic visualization and analysis, combining data collected from distributor systems with network topology information, displayed using thematic maps and multidimensional views. Specific functionalities for utility companies are included.
The integration of installation events, load balancing and consumption data in combination with tools provided by Topos allow for a broad analysis of georeferenced cause-effect relationships, creating a powerful environment to support decision making and combat non-technical losses.