Present and Future of IoT Analytics

For instance, such classes can be "healthy" or "unhealthy", which is the type of prediction one would want to make for an IoT device. Supervised models are more directly usable, typically come with an estimate of their accuracy, and are thus preferred for many applications. However, until issues with data quality - including the ground truth data quality - are resolved, achieving high accuracy is hardly possible for supervised models.

Action: Focus on "unsupervised" modeling today, but build an infrastructure that is compatible with "supervised" models, and continue improving the quality of data. Transition to supervised models can and will happen gradually as infrastructure is put in place to automatically label data.

Trend: Automated analytics.

Challenge: Lack of algorithm transparency limits scalability due to human workload.

The ultimate goal for IoT analytics is to fully automate tasks that can be automated, freeing human experts to focus on the most complex problems. This is the most efficient and cost-effective way. However, most of the machine learning (ML) algorithms are the so-called "black box algorithms" and the decisions they make are often hard to interpret and trust.

Action: Invest in people training, education, and building trust in models used. Also, invest in solutions that can interpret models’ answers for human users. The more transparent models' responses are, the faster analytics automation becomes a reality.

Trend: Migration to the cloud.

Challenge: Data connectivity issues, analytics decision latency, and infrastructure cost.

Action: Migrating data, IoT analytics, and other services to one cloud makes perfect sense in many cases. After all, the cloud offers scalability, elasticity, and a pay-as-you-go approach, allowing decreased capital expenditure. On the other hand, relying on the cloud for near-real-time IoT analytics might be impossible in some cases due to the data latency issues.

Action: Plan for a flexible, integrated, and reliable end-to-end analytics solution, from the onboard/edge analytics to powerful cloud-based analytics. When such a solution is available, use it all or its parts to address connectivity, latency, and cost.

Trend: A shift from data batching to streaming and real-time analytics.

Challenge: Complexity of changing the existing infrastructure.

The general trend in analytics is to shift from batch data processing to real-time processing. The cost of such a shift could be high, especially when installed infrastructure is extensive.

Action: Plan for the future - this transition will take place regardless of immediate needs. Customer requirements, technological advances, and competitive pressure will eventually support more streaming applications.

Trend: Ubiquitous access to IoT data.

Challenge: Data IP, ownership, security, and governance.

Having all IoT data in one place, and giving all teams access to all the data, could bean excellent way to accelerate product and technology development, reduce cost, innovate, and improve collaboration across the company. However, questions arise – who owns which data, who can access which data, do we have the rights to use the data as proposed, or how should we handle highly-confidential and harmless data in the same cloud. There are evolving regulations, industry standards, best practices, and user expectations, that need to be considered together to support use of IoT data.

Action: Invest in robust data governance and security process. Leverage services available from the major cloud service providers where possible, recognizing that they may only offer a floor from which an organization can build on.