Power BI & More Ulrik Carlsson

This episode has been brought to you by KingswaySoft.
The new Customer Insights with Matt Wittemann.
Dynamics 365 and CRM legend Matt Wittemann joins the podcast to discuss the Customer Insights solution that was made generally available recently.
Customer Insights have been in preview for a few years. During this time they have been some iterations of the solution, features have come and gone, and has now landed on a solution tailored to analyzing customer profiles and people using varying data sources. Listen in as we go through the feature set, to get clarity on who this product is for, and why it’s great solution for those companies.
 
You can read more about Customer Insights on Matt Wittemann’s blog here https://mattwittemann.com/
And the documentation from Microsoft. https://dynamics.microsoft.com/en-us/ai/customer-insights/
Don’t forget to follow Matt on Twitter @MattNC

This episode is brought to you by by Maplytics by Inogic.
 
Data Scientist Matt Lamb and Microsoft MVP Ulrik Carlsson discusses how you create product recommendation engines. A separate discipline in data science, combining content filtering and collaborative filtering, to do targeted  product recommendations is not only more difficult, but possibly also one of the most lucrative.
Episode also includes in discussions on:
Combining advanced customer profiling with transactional data.
 
Matt talks to his new product PinPoint, a product recommendation engine for the Aftermarket How Content Filtering and Collaborative Filtering combined can make for advanced product recommendations Why Ulrik doesn't like continued recommendations from Amazon to buy smoke detectors when they perfectly well know he already has two (and how to tune your algorithm to avoid annoying your customer). Possible data science urban legend on Target identifying teenage pregnancies before concerned parents of pregnant teen knows about it. Will Matt this time give a concrete answer to the question on how many records are needed to get good results from these algorithms?  
 
Links: PinPoint for Aftermarket

This episode is brought to you by D365UG.
Matt Lamb joins Ulrik Carlsson again to talk about the use of data science in Field Service implementations and why Field Service implementations are particularly interesting. The wealth of data can be used for both advanced machine learning scenarios to predict failures, creating advanced DAX formulas in Power BI to optimize Work Order scheduling, and why you might want to create your own ranking of Work Order as opposed to what is delivered out-of-the-box.
 
Topics discussed:
What’s special about Field Service? Telemetry and IoT data Vibrations as a predictor Regression algorithms and Binary Classifications Service Level Agreements The Weighted Average Optimization Equation

In this episode (brought to you by KingswaySoft), Ulrik Carlsson talks about changes to the experience of embedding Power BI in Dynamcis 365 and what is new in the April 2019 update for Power BI Desktop.
Discussed in this episode:
Changes to embedded experience Making your embedded reports visually match d365 Licensing implications Security implications Embedded reports and change management April updates for Power BI Desktop Updates to PowerApps visuals Automatically refreshing the data set Key influencer visuals Data Flows are leaving preview Pervasive artificial intelligence Got any questions for the chart guy? Send them to voice@crm.audio.

In this episode (brought to you by mscrm-addons.com), Matt Lamb, Data Science and Commercial Analytics Lead at eLogic, rejoins the podcast to discuss what we need from our Dynamics 365 implementation when stepping into Machine Learning and AI. What do we need from our Dynamics 365 data in terms quantity and completeness to get effective results? What are the ways to deal with incomplete and what consequences does it have on your Machine Learning results when you make even simple updates to your business processes. In order to create a record set to use as a base for Machine Learning, you may not need as many records as you think, but need to strike the right balance of quantity and quality.
In this episode we discuss:
o    How many records are really needed for effective machine learning?
o    What structure and maturity level of data is needed?
o    Supervised vs. Unsupervised Learning
o    How many people does Matt’s dog need to meet?
o    What happens with your algorithms when you make changes to your business process?
o    Tips to make your data scientist happy
Got questions or suggestions for future episode? Email voice@crm.audio.
This episode is a production of Dynamic Podcasts LLC.

In this episode (brought to you by D365UG), Ulrik interviews Matt Lamb, Data Science and Commercial Analytics Lead at eLogic

Matt Lamb joins the podcast to discuss his work and background as a Data Scientist and shed some light on what a full-time Data Scientist actually does and what skills are required. Find out how a data scientist defines the term AI and how that relates to the various disciplines of machine learning, deep learning, and statistics. Also, what can data science add to your solutions now that Microsoft is adding out-of-the-box AI features to Dynamics 365.

Data Scientist background and training What is AI vs Machine Learning, Neural Networks, and Statistics The three work areas of the data scientist AI in Dynamics 365 vs a Data Scientist.
Got feedback or suggestions for a future episode? Email voice@crm.audio
Links
Matt Lamb blog posts: https://elogic.com/Blog/PID/473/authorid/31/AuthorName/Matt-Lamb