Ernst & Young Global Ltd. (EY) has introduced a new service for manufacturers that leverages large volumes of both structured and unstructured data for use in predicting equipment reliability.

Built on SAP SE’s HANA database, SAP HANA Vora software, SAP^– Predictive Analytics and Hortonworks Inc.’s Data Platform (HDP), the EY Predictive Reliability Analytics service provides a full review of relevant data to help clients manage costs and detect potential fraud, set reserves and improve product reliability to reduce unplanned down-time, EY said. This enables manufacturers to make faster and more targeted decisions to improve quality and reduce warranty costs through EY’s Warranty Analytics service offering for SAP HANA and Hadoop.

Introduced last July, Warranty Analytics applies EY algorithms on top of SAP technology to monitor warranty claims to identify fraudulent activity, as well as other cost-reduction and quality-improvement opportunities.

“Warranty Analytics helps automotive companies leverage large volumes of both structured and unstructured data and convert impossible warranty challenges into actionable intelligence,” said Chris Sullivan, vice president of global channels & alliances at Hortonworks, in a prepared statement.

EY estimates that auto makers typically spend up to three percent of annual revenues paying warranty claims. Aside from the direct financial impact, these claims can carry substantial indirect costs, such as damage to brand image, loss of customer loyalty and even legal liability, as epitomized by Toyota Motor Corp.’s sudden acceleration crisis a few years ago. It can also take months for auto makers to assemble enough data to perform the analytical routines needed to take preventive measures.

EY said the Internet of things (IoT) will revolutionize the way data is collected and managed in the field, helping manufacturers better anticipate and resolve problems, improve product design to avoid expensive in-field repairs.