Improving tracking & forecasting for Canada’s leading billing software solution

A company providing subscription and usage billing and rating solutions for data, voice, SMS and API usage. The company’s SAAS platform allows its customers to monetize in real-time any triggered event in the connected network of hundreds of millions of IoT devices.

Today’s Telecom, IT and Utility companies are looking for reliable billing solutions that provide accurate data reporting. The efficacy of usage-based billing models is predicated on collecting, analyzing and forecasting event information from millions of IoT devices in real-time. For decades, businesses have lost millions of dollars due to irregular tracking, anomalous data and an inability to forecast.

As a leader in billing and reporting software, our client was looking to improve their overall accuracy to help mitigate risk and drive cost-savings on behalf of their customers.

Our analysis revealed that a 1% increase in tracking and forecasting accuracy could save millions of dollars for our client’s customers. Based on this insight, we built a state of the art, proprietary model that offered unparalleled accuracy versus the industry-standard, time-series tracking algorithms. We integrated the model using industry-standard web services within our client’s monitoring and production infrastructure, and improved the accuracy of the software from 90 to 93%, delivering a strong ROI for our client’s customers.

Crater Labs created a unique deep learning model capable of analyzing irregularly spaced, non-stationary time-series data, identify anomalies and predict when and with what confidence the next anomaly would occur.

Our model improved anomaly detection and billing accuracy by 3 percentage points, unlocking millions of dollars in savings for our client’s customers.

The new solution enabled our client to detect issues faster, while mitigating risks and driving efficiencies on behalf of their customers.