Digital Mortar

Of all the things I’ve worked on in my career, few have given me more satisfaction than the X Change Conference. Building a conference around conversation among peers always felt to me like the best kind of conference. And delivering that within a place and location that?made people feel great ended up creating something a lot of people thought was special. My good friend and long-time colleague Kelly Wortham his bringing something similar to life with the Experimentation Island. It’s a small, peer-focused experience in a really cool location with a core set of great people to help set the conversation. Few subjects reward sharing and collaboration like experimentation (because no matter how expert you are, the range of possibly interesting experiments is infinite and, like the universe, expanding rapidly).?If you’re not getting much value from your existing conference schedule, check it out. I think you’ll find that the joys and learnings of a small, carefully curated, conversation-based conference make all your other conference events seem kind of pedestrian. https://lnkd.in/gD2eAt-d

Tune in to hear from Gary Angel, the founder & CEO of Digital Mortar, as he discusses how AI and other cutting-edge technologies are revolutionizing retail analytics and physical retail spaces, with a special focus on enhancing the in-store customer experience. About our guest, Gary Angel: Considered one of the leading customer analytics and digital measurement experts in the world, Gary is the CEO and founder of Digital Mortar. Digital Mortar provides comprehensive collection and measurement of the customer journey in retail stores. Previously, Gary led Ernst & Young’s Digital Analytics Practice. EY acquired Gary’s last venture – Semphonic - in 2013. President and founder, Gary grew Semphonic to be the leading digital analytics practices in the United States. Voted the most Influential Industry Contributor by the Digital Analytics Association, Gary blogs on LinkedIn and the DigitalMortar website. His book, Measuring the Digital World, was published in 2016 by the Financial Times Press. Linkedin: https://lnkd.in/e8M2Rcc8 Website: https://digitalmortar.com Guest Host: Cole Koumalats, PMP, CFI Producer: Sachin Kumar Bhate Sponsor: Proxima360 | https://proxima360.com About Retail Corner #Podcast: Listen to other podcasts at: https://lnkd.in/eGwTK9_T or https://retailcorner.live Subscribe to our podcast: Apple iTunes: https://apple.co/3eoeUdT Spotify: https://spoti.fi/3dvjpDJ Google Podcast: https://bit.ly/3DFHXHw Amazon Music: https://amzn.to/3tkbhk1 Interested in being on our podcast? Submit your request via [email protected] #customerbehavior #retail #brickandmortar #physicalretail #analytics #AI #optimization

Wrapping up my series on Lidar Data Quality After writing a whole series on lidar data quality and how to improve it, here's some reflections and key takeaways. First and foremost, writing a bunch of posts about lidar data quality and cleaning techniques makes it seem like the data must be pretty bad. It’s not. People measurement sensors have improved dramatically in the five plus years I’ve been at this, and lidar is one of the key reasons. Lidar does an excellent job of object identification and high frame-rate precise tracking of movement. It supports almost every people-measurement and flow-analytics use-case we’ve found, including some of the most demanding ones (at opposite ends of the spectrum, full journey tracking and real-time device control). That being said, data quality is the single most important aspect of any analytics system. Data quality is never, ever perfect and it's usually not as good as the analyst would like. I’ve spent decades in analytics, and I’ll just reiterate what every user of data will tell you – data quality is always a problem. It’s a problem because analytics starts out hard and the more noise you put in the system, the harder it gets. It's also really important to realize that from a flow-analytics perspective, data quality is not one number. The biggest mistake I see in people-measurement RFPs is the assumption that data quality is a specific thing that can be represented by a single number like 95% accuracy. That’s wrong. Data quality is specific to use-case, environment, and conditions. And anyone who tells you different is either ignorant or lying. It can vary dramatically by time of day and crowd, and it can be totally different for a measurement of line length vs. task completion time. We get asked for these numbers all the time in RFP’s and we grit our teeth and do our best. But we always try to explain the real facts on the ground. Finally, and this is the biggest takeaway, the data quality that comes from your sensors and Perception software isn’t the final data quality you can or should expect. I’ve never run into a situation where the data quality couldn’t be significantly improved with intelligent post-Perception software. There are a host of techniques for improving data quality from eliminating bad object identifications to improving object classification to fixing track breakage. In these past few posts, I’ve tried to provide some fairly detailed guidance to the DIYer on how to get better lidar data. But if you just want to consume high-quality lidar data as quickly as possible, consider our DM1 platform. Even if you don’t need all the viz tools and analytics, you can take full advantage of the cleaning and distribution layer that underpins the whole system and gives you direct access to significantly better flow analytics data.

Cleaning and improving #lidar data quality for real-time applications is particularly challenging. But even down at the 100ms level, there are at least a few things you can do to improve the data: