Industrial IoT

8 Differences Between IoT Data & Mobile/Web Data

5 min readThe Internet of Things (IoT), while transformational, is the biggest data challenge plaguing [...]

5 min read

The Internet of Things (IoT), while transformational, is the biggest data challenge plaguing product manufacturers today. With its own set of challenges, IoT data has nuances that require a highly specialized approach to data analysis.

It requires specific analytic tools that the traditional/general-purpose big data, web or mobile analytics suites cannot provide. Tools used to analyze IoT data require a different approach entirely.


This blog post highlights 8 key differences:

  1. Diversity & Volume of Data Sources
  2. Diversity of Data Models
  3. Presence of ‘Dirty Data’
  4. Variety of Use Cases
  5. Choice of Integrations
  6. Aggregate vs. Individual Analysis
  7. Cross-Functional Personas
  8. Domain Expertise


IoT data is derived from a plethora of devices where data type and cleanliness are often inadequate for processing.  Rotation speed from magnetic bearings, temperature, flow, and pressure from industrial compressors, etc, are all analog and generated by custom devices that are sometimes more than twenty years old.  In addition, a single device can have a dozen data sources from a variety of sensors. The data ingestion pipeline needs to provide all the tools necessary to prepare the data, correlate them, and create a time-series based graph of the observed behaviors.


You can have thousands of enterprise implementations in mobile analytics, but they will still be tracking the same thing – taps, clicks or logins. Basically actions from the end-user.  While there may be differences between a gaming application and a travel application, the data model and the outcomes you are trying to achieve will be very similar. Now, if we compare this to getting 3-axis vibration signals from a magnetic bearing versus flour/water/oil levels and usage from a bread maker… it’s very different!  In fact, in the IoT, you end up having a different data model for every implementation. It is critical to spend time building an infrastructure that can handle a different data model for each tenant.


Mnubo's SmartObjects IoT Data Modeller

Mnubo SmartObjects IoT Data Modeller



Everyone underestimates how ‘dirty’ IoT data is. Biases and outliers exist everywhere in the data, just how/where the sensor is placed will actually introduce bias. This is a concept unknown to web/mobile analytics, given that all the ingested data comes from a human (ok, maybe some bots) clicking/tapping on a page/app. As you can imagine, this poses a problem for data engineering, machine learning, and the necessary iterative re-training.


In mobile and web, analysis are very well defined: user sessions, page loads, clicks and taps, time spent, etc. Irrespective of the website or mobile application, the metrics are always known. With IoT data, each use case has its own set of custom metrics to be analyzed: charge time of electric cars, cooling time for a plastic molding machine, deflation rate for tires and so on. Each use case will gather custom sensor data to form a coherent view of the problem to analyze. An IoT Data Analytics platform must be able to assemble the right metrics and sequences to generate insights on a per device or per use case basis.


Mnubo's SmartObjects IoT Data EV Charger Demo

Mnubo’s SmartObjects EV Charger Demo



Another big difference between mobile/web data analytics and IoT is the type of systems you end up integrating your ‘actionable’ insights with. In mobile/web, it’s most often consumed in dashboards and integrated with marketing tools/campaigns. Whereas with IoT data, there are hundreds of processes and systems that can consume the insights.


With most web/mobile analytics implementations, it is sufficient to look at ‘aggregates’ – for example, the total number of ‘actions’ every 15 minutes/hour/day.  The individual actions are less important. With IoT data, one sensor reading can be the key to detecting a weakness or future failure so your system actually needs to index and keep all data (at least until it is deemed useless). Moreover, the algorithms needed in IoT are diverse: optimization, classification, time-series predictions, etc. Whereas the web/mobile algorithms are most often about clustering end-users.


Aggregate view in Mnubo’s SmartObjects IoT Data Platform

Aggregate view in Mnubo’s SmartObjects Platform


Aggregated score for Individual asset in Mnubo’s SmartObjects IoT Data Platform

Aggregated score for Individual Asset in Mnubo’s SmartObjects Platform



Unlike web and mobile analytics, where the user personas are well defined: digital marketing, product managers, etc. IoT Data Analytics serve several cross-functional personas who require insight into a variety of metrics or KPI’s. A product manager will want to see device usage, a field technician will need to get anomaly detection, alerts and maintenance history, an operations manager will want predictive maintenance recommendations.  In IoT, very few data scientists are available, which makes the importance of out-of-the-box insights (focused on IoT use cases) critical.


An IoT analytics expert / data scientist must recognize the value of domain expertise and how hard it is to do without.  An IoT platform needs to enable easy sharing and collaboration between domain experts and data scientist. In mobile/web, typically the user is an digital marketing guru or a ‘growth hacker’ who both gets the ‘analytics’ piece AND the ‘domain expertise’ piece. This is not the case in the IoT where horizontal analytics platform ingest and manage data across verticals.


Interested in hearing more?
Request more information now.