Predictive device maintenance

A computer program product for predictive device maintenance, the computer program product comprising:

• one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions comprising:
• program instructions to generate a risk score for an Internet of Things (IoT) device as a weighted measure of input data about the IoT device and a frequency of failure of the IoT device, wherein:
• the input data comprises documents describing the IoT device and a plurality of customer reviews of the IoT device, and wherein the input data is found from crawling a web and found in libraries;
• and
• the risk score indicates an estimate of loss of function of the IoT device;
• program instructions to adjust the risk score by a weight based on the plurality of customer reviews;
• program instructions to determine an optimal time to trigger a predictive notification pertaining to the IoT device based on the risk score;
• and
• program instructions to issue the predictive notification at the determined optimal time.

A system for a plurality of Internet of Things (IoT) devices, comprising a processor operably connected to a memory, the memory containing program instructions to, when executed on the processor:

• generate a risk score as a weighted measure of input data about an Internet of Things (IoT) device and a frequency of failure of the IoT device, wherein the risk score indicates an estimate of loss of function of the IoT device;
• determine an optimal time to trigger a predictive notification pertaining to the IoT device using the risk score;
• and
• at the determined optimal time, issue the predictive notification.