Cloudera machine learning platform used to crunch IoT data from millions of connected cars.
Octo Telematics says it has analysed 186 billion miles of driving data from connected cars and used a cloud-based machine learning and analytics platform to predict and model driver risk from the data.
The firm used the cloud platform from Cloudera to gain insights for over 100 insurance companies around the world. Octo Telematics’ platform, built on Cloudera Enterprise, aggregates over 11 billion new data points daily from 5.4 million connected cars and sensors.
The company said that every relevant type of contextual, driving, behavioural, and crash data is used to forecast individual driving habits, improve crash notifications and responses, evaluate crash dynamics, and detect fraud.
20 million miles of road
By running data between cloud and on-premise environments via Cloudera Enterprise, Octo Telematics is able to store, process, and analyse data that reflects over 20 million miles of driving per minute, it said. The captured data includes a range of telematics insights, including location, acceleration, braking, idling, collisions, and cornering.
The processed data is then made available to analytics algorithms that revolve around driver risk-scoring and modelling, pricing, accident reconstruction, claims management, crash analysis, driver behaviour, and vehicle health.
Octo Telematics said that by building machine learning models on this massive and constantly updated data set, it can formulate more accurate predictions and risk models for individual drivers. Plus, modellers can test new ideas and techniques two times faster, refining them on the fly to produce innovative products and services – using data volumes that have never been possible before.
“Octo Telematics needed the flexibility, agility, and scale to run its machine learning risk models and predictive applications, both in the cloud and on premise, to meet service-level and economic goals,” said Dave Shuman, IoT and manufacturing industry leader at Cloudera.
“Using Cloudera Enterprise to replace a bespoke data platform, Octo has been able to increase its capabilities to scale with the explosion of data volumes and analytic workloads. With Cloudera, they have been able to transform the automotive insurance industry, and these capabilities translate into better outcomes for consumers and underwriters.”
Internet of Business says
Fast forward to a world of autonomous vehicles, fleets, and driverless cars and it stands to reason that a smart, connected vehicle won’t just update itself every day with data about how it has been used, but also with the data about how every other vehicle like it has been used worldwide. The long-term implications of that global data stream could be extraordinary in terms of making travel faster, safer, more efficient, and more sustainable.
IoTBuild is coming to San Francisco, CA on March 27 & 28, 2018 – Sign up to learn all you need to know about building an IoT ecosystem.