How can an organisation optimise its sales channels and product targeting by building a 365-degree view of its customers in Dynamics CRM? The answer, and topic of this session, is with the help of Azure IoT and Machine Learning services!
The use case described is the identification of common patterns of actions by consumers, classification based on criteria like age, gender, location, etc., and promotion of best-fit products and services. To achieve this objective, wearable and mobile devices are used and connected to the Azure IoT Hub for collecting information about location, commuting patterns and weather condition. All this information is then scored and evaluated in Azure Machine Learning to predict the best matching products and services.
Targeted at software architects, developers and product owners, this session focusses on presenting all the technologies used to build the discussed use case and how to integrate them in an end-to-end fully functional solution.
Sales Effectiveness in Dynamics CRM with Azure IoT and Machine Learning
Churn rate is a measure of customer attrition, and is defined as the number of customers who discontinue a product or service during a specified time period, divided by the average total number of customers over the same time period.
Predictive maintenance: Anticipate maintenance needs and avoid unscheduled downtime by connecting and monitoring your devices for predictive maintenance.
Remote monitoring: Connect and monitor your devices to analyze untapped data and improve business outcomes by automating processes.
Azure IoT Hub is an Azure service that enables secure and reliable bi-directional communications between your application back end and millions of devices. It allows the application back end to receive telemetry at scale from your devices, route that data to a stream event processor, receive file uploads from devices, and also to send cloud-to-device commands to specific devices. You can use IoT Hub to implement your own solution back end. In addition, IoT Hub includes a device identity registry used to provision devices, their security credentials, and their rights to connect to the hub.
Device identity registry
Block unsolicited network information
Authorisation and authentication are based on per-device identities
Bi-directional communication
Communication between device and service is secured
Maintains device specific queues for all sent commands
For your machine learning model to provide predictions, the model must first learn from known data in a process known as training. During training, data is evaluated by the machine learning algorithm, which analyzes the distribution and type of the data, looking for rules and patterns that can be used later prediction.
Scoring is the process of applying a trained model to new data to generate predictions and other values.
You can use Evaluate Model to measure the accuracy of a trained classification model or regression model. You provide a dataset containing scores generated from a trained model, and the Evaluate Model module computes a set of industry-standard evaluation metrics.
The metrics returned by Evaluate Model depend on the type of model that you are evaluating:
Classification Models
Regression Models
Clustering Models