The Measurement Minute: Recent Episodes
Gary Angel
The Measurement Minute by Gary Angel One of the biggest challenges to doing people-measurement is the cost and hassle of the cabling. Deploying standalone single sensors has always been possible. But when data needs to be fused across multiple sensors to track customer journey, each LiDAR sensor must be connected via a home-run (a … Continue reading "Look Ma, No Wires!"
The Measurement Minute by Gary Angel One of our clients at Digital Mortar is a chain of gas/convenience stores measuring the full journey from pump to shop and back. What makes their use-case more compelling is that the stores are a significant upscale from your traditional gas convenience mart – with lots of more … Continue reading "Measuring Journeys from Outdoors to Indoors"
The Measurement Minute by Gary Angel Although Digital Mortar isn’t really focused on loss prevention or security applications, there are two big reasons why it matters if you’re thinking about people-measurement. First, there are times when you can dual-purpose sensors to do both crowd-analytics and security (which greatly improves your hardware ROI). Second, when it … Continue reading "People Measurement Alerting for Security and Perimeter Monitoring"
The Measurement Minute by Gary Angel Customer Journey alerting can completely transform the experience of a physical space. Instead of waiting for a customer to seek out help, it actively looks for opportunities to use the available help most effectively. Common use cases include identifying customers who absolutely require assistance (unmanned support, locked cases, … Continue reading "Customer Journey Alerting with People-Measurement"
The Measurement Minute by Gary Angel While performance may be the biggest challenge in building a people-measurement based alerting system, the most important problem for most businesses to solve is HOW to use people-measurement alerting. Use-cases tend to fall into one of these basic categories: operational management, customer journey, and security / loss-prevention. Of … Continue reading "The Operational Use-Cases for People-Measurement Alerting"
The Measurement Minute by Gary Angel The visible part of an alerting system – the text alerts, webhooks and emails users get – is the easy part. The hard parts are building the realtime pipeline for store or location measurement, creating things like the predictive queue model, and keeping the underlying alerting engine performant … Continue reading "The Challenge of a Real-time People-Measurement Alerting System"
The Measurement Minute by Gary Angel Productionizing a predictive queue measurement model really involves solving two problems. The first is integrating the predictive queue model into a real-time pipeline so that you can generate predictions about future line states based on current data. The second problem is deciding what to do about those predictions … Continue reading "Productionizing a Predictive Queue Management Model"
The Measurement Minute with Gary Angel Building a predictive queue management model is the penultimate and most interesting step in the process of building a queue management system. We used two different analytic techniques to tackle the problem: classic time-series and neural networks. The advantage of time series is that it is simple, easy … Continue reading "Building a Model for Predictive Queue Analytics"
The Measurement Minute by Gary Angel Probably the most important step in building a model is making sure you’ve got the right target variable. Usually that’s not too hard. But looking at our line data, we quickly realized that predicting line depth wasn’t going to work as straightforwardly as we thought. The problem is … Continue reading "Getting the Right Target Variable for Line Prediction"
The Measurement Minute by Gary Angel After the data wrangling comes the fun part of any analysis – building the actual model. That starts with model selection. For predictive queue management, we’re looking at time-series models. And because we have store traffic and occupancy data, it will be a multivariate model. In addition, it’s … Continue reading "Choosing a Model for Predictive Queue Management"
The Measurement Minute by Gary Angel The hardest part of most analytics projects is the data wrangling – and so far that’s proven to be the case when it comes to building a predictive queue model to incorporate into our DM1 platform. I’m working with data from multiple clients and while the core data … Continue reading "Data Wrangling for Predictive Queue Analytics"
The Measurement Minute by Gary Angel The hardest part of most analytics projects is getting and prepping the data. For predictive queue management, we’ll use an event level feed from Digital Mortar’s DM1 product. It gives us every piece of data we might want. The hard part, is deciding what we might actually want … Continue reading "Predictive Queue Management: Data Preparation for Analysis"
The Measurement Minute by Gary Angel A recent article in CNN detailed the steady growth in self-checkout despite a litany of problems for both customers and stores. Is the trend truly driven, as the article suggests, by a fundamental misconception that self-checkout is faster? Whatever you think about self-checkout (I happen to like it), … Continue reading "Measuring Self-Checkout. Or not…"
The Measurement Minute by Gary Angel A customer’s time in line is one of the most important (and controllable) aspects of physical experience. We’re currently working through several queue management projects that will involve both active queue management (alerting when lines get long) and – even more interesting – predictive queue management (alerting when … Continue reading "Introduction to Predictive Queue Management"
The Measurement Minute by Gary Angel Celebrating 50 years since their landmark study The Limits to Growth, the co-editors of a retrospective look back manage to seem as smug and wrong-headed as ever in this Wired interview: https://www.wired.com/story/the-infamous-1972-report-that-warned-of-civilizations-collapse/ It’s awfully hard to model the world but a deep ignorance about economics and … Continue reading "On the Limits to Growth and the Limitless Hubris of Modelers"
The Measurement Minute by Gary Angel Integrating Shopper Journey and Point-of-Sale (PoS) data at the store-section/time level delivers powerful analytics around true conversion rate, optimal STARs rate, section seasonality, out-of-stock impact and more. But what about integrating PoS at the individual level – so that specific baskets are attached to specific journeys? More … Continue reading "The Analytics Power of Integrating Individual Shopper Journey and Point-of-Sale Data"
The Measurement Minute by Gary Angel The value of a PoS integration to journey data is profound. And that value starts with one essential metric – the true conversion rate. Journey tells you how much traffic every area of your store got. How much of that traffic engaged. What it doesn’t tell you is … Continue reading "Key Analytics with Point-of-Sale (PoS) Data at the Store Section Level"
The Measurement Minute by Gary Angel The key to a successful integration of PoS data into Shopper Journey data isn’t usually the join itself – it’s having a good mapping of SKU to store. That mapping is essential even if you’re doing a join at the individual level, because it’s the only way to … Continue reading "Shopper Journey and PoS Integration : Mapping SKUs to the Store"
The Measurement Minute by Gary Angel Given that PoS data is a powerful addition to shopper journey data, the question becomes what level of PoS data integration is necessary or appropriate. The most powerful integration is also the most detailed – integrating purchase data into individual journeys. This kind of integration let’s you see … Continue reading "Choosing the Level of PoS Data to Integrate into Shopper Journeys"
The Measurement Minute by Gary Angel Yes, Point-of-Sale (PoS) data enables a host of really fundamental analytics opportunities in store journey measurement – from both the journey and the store perspective. It also helps ensure that key shopper journey metrics mean what you think they mean. But probably the most important role PoS data … Continue reading "Why PoS Data is a Fundamental Integration with Shopper Journey Data"
The Measurement Minute by Gary Angel PoS is the motherlode of retail integrations with shopper journey data. It’s almost a must-have. But all integrations can be frightening – less for the technical challenges than for the analytic ones. When you start down the path of PoS integration with in-store customer behavioral data, you’ll want … Continue reading "Integrating PoS and Shopper Journey Data"
The Measurement Minute by Gary Angel Dynamic associate allocation is one of the most powerful applications of people-measurement in retail – particularly for larger stores. But when it comes to implementing dynamic allocation, there isn’t one strategy that fits every need. Fortunately, advanced people-measurement provides enough detail to support a variety of different techniques. … Continue reading "Strategies for Dynamic Associate Allocation"
The Measurement Minute by Gary Angel Real-time store journey data creates opportunities to manage the store in ways that have never existed before. It lets managers or software dynamically allocate Associates to tasks and even specific customers. That’s what the military calls a force multiplier – letting a fixed number of Associates do more. … Continue reading "Dynamic Real-time Associate Allocation"
The Measurement Minute by Gary Angel Greeter interactions form a special sub-class within a more general scheme of Associate/Shopper interaction classifications. It’s easy enough to identify Greeter interactions (based on where they occur), but it’s also possible to create a more comprehensive and detailed look at Greeter-specific classifications if you’re trying to optimize greeting … Continue reading "Classifying and Analyzing Store Greeter Interactions for Store Analytics"
The Measurement Minute by Gary Angel Unlike the Call-Center, there’s no easy way to classify what kind of interaction an Associate had with a shopper on the floor. That means we have to rely on behavioral classification for analysis. Fortunately, it’s relatively easy to distinguish between the most basic types of shopper and Associate interaction. … Continue reading "Classifying Associate Interactions in the Store with Shopper Journey Data"
The Measurement Minute by Gary Angel The single most important Associate measurement is probably interactions. After all, shopper interaction is the whole point of having Associates on the floor. With basic interaction measurement, the key metrics are probably interaction rate (the % of shoppers in a section with an interaction) and interaction conversion rate … Continue reading "Introduction to Advanced Associate Interaction Metrics"
The Measurement Minute by Gary Angel Groups of shoppers can have a surprisingly large impact on Key Performance Indicators (KPIs) like conversion rate and STARs. If you only focus on individual shopper counts, you may be getting a misleading view of performance. Metrics like conversion rate will shift significantly when groups are taken into … Continue reading "How to Measure Shopper Groups in the Store"
The Measurement Minute by Gary Angel Measuring shopper groups is important – not least because it has a huge impact on conversion rates. Shoppers in groups reduce total opportunity – and because the percentage of shoppers in groups can vary wildly by day-time part and section even at the same store, conversion rates that … Continue reading "Measuring Shopper Groups and the Impact on Store Conversion"
The Measurement Minute by Gary Angel The third component of a good high-level store dashboard based on people-measurement should focus on operational efficiency. Associates are a huge part of a store’s operational efficiency and cost. They are also, without doubt, the most variable component of performance. For a dashboard, you’ll want to measure … Continue reading "Dashboarding Store Operational Efficiency with People Measurment"
The Measurement Minute by Gary Angel Any good dashboard of store performance based on shopper data should cover shopper quality, merchandising effectiveness and operational efficiency. The last minute covered shopper quality, this one covers merchandising effectiveness. It’s probably the single most important part of a good store report. After all, merchandising is the heart … Continue reading "Dashboarding Shopper Journey Data : Merchandising Effectiveness"
The Measurement Minute by Gary Angel A good store dashboard should provide context on the big picture KPIs of traffic and conversion. To do that, it should show shopper quality, merchandising performance and operational efficiency. Of these, measuring shopper quality is by far the hardest – because it’s very difficult to distinguish the root … Continue reading "Measuring Shopper Quality with Behavioral Analytics and People Measurement"
The Measurement Minute by Gary Angel Though the best uses of shopper measurement data often involve focused analysis to answer a specific business question, there’s both a need and real value in making store measurement data more accessible. Often, that translates into a demand for KPIs and dashboarding. That can be challenging, because the … Continue reading "Store Dashboarding with Behavioral Analytics"
The Measurement Minute by Gary Angel Retention has become a critical problem for many businesses and for retailers, current retention woes are just icing on an already dismal cake. Churn rates in retail are staggering – and that was true even pre-pandemic. Many new employees don’t last a year. Almost half don’t last 90 days. … Continue reading "Measuring the Impact of Associate Churn"
The Measurement Minute by Gary Angel While flexible digital mapping and a generalized alerting system can cover a very wide variety of real-time applications, queue management usually requires special customization. Metrics like stations open and estimated wait time don’t fall out of standard people-measurement. Mostly, they aren’t super complicated but they are often just … Continue reading "Real-time Queue Management and Alerting Customization"
The Measurement Minute by Gary Angel Real-time people-measurement creates an array of valuable operational and marketing opportunities. Those opportunities usually involve an alerting capability built on top of the real-time feed. In this Minute, the benefits of combining a flexible space mapping system and a generalized alerting system are described. By putting the two … Continue reading "Alerting in People-Measurement"
The Measurement Minute by Gary Angel In The Age of Customer Equity, Allison Hartsoe tackles the journey companies must take to understand and value their customers appropriately. A long-time customer analytics expert, Allison’s new book is a great read and a powerful introduction to putting customer value at the center of your business and your … Continue reading "The Age of Customer Equity: An Interview with Author Allison Hartsoe"
The Measurement Minute with Gary Angel A real-time data pipeline for shopper journey data creates all sorts of challenges, and one of the biggest is handling Associate detection. If your using realtime data to dynamically move Associates to the right places in the store, it’s critical that you know who’s a Shopper and who’s … Continue reading "Optimizing the Store Real-time Shopper Journey Pipeline with Associate Detection"
The Measurement Minute with Gary Angel Are real-time analytics valuable? Usually, not so much. So why are we spending a boatload of time adding a true real-time pipeline to our DM1 people-measurement platform? It’s because real-time data opens up a number of powerful store use-cases for operational improvement and even loss prevention. From occupancy and … Continue reading "Real-time People Measurement: Analytics and a Whole Lot More"
The Measurement Minute by Gary Angel With today’s advanced people-measurement technologies, it’s not that hard to measure when Associates are interacting with Shoppers. This interaction measurement delivers a whole array of useful metrics and analytics opportunities. From measuring basic interaction counts, cross-tabulating interactions against shopper engagement, correlating interactions to checkout and basket size, and … Continue reading "Measuring Shopper/Associate Interactions"
The Measurement Minute by Gary Angel Measuring Associates is an unexpected benefit of doing powerful in-store shopper measurement. But when it comes to making sense of Associate data, the metrics that work for shoppers don’t always apply. There’s little point in measuring Visits, Lingers, Draws or Dwells – all core shopper journey metrics. On … Continue reading "Store Associate Metrics"
The Measurement Minute by Gary Angel The traditional calculation of Shopper to Associate Ratios (STARs) is simple: Door Count divided by the number of Associates staffed that day. But when you start doing full journey measurement, you’re measuring areas inside the store at much finer increments of time and suddenly it’s not so clear … Continue reading "Measuring Shopper to Associate Ratios (STARs) – You’re not in Door Count Land anymore"
The Measurement Minute by Gary Angel Measuring Associates is a vital part of effective in-store measurement. It’s necessary to ensure proper shopper counting and it’s interesting in it’s own right. But there are two different strategies for measuring Associates – badging and passive detection. Both work, but there are some distinct advantages to passive … Continue reading "Retail Associate Measurement Strategies"
The Measurement Minute by Gary Angel Knowing the state of the store is essential for shopper journey analytics. You have to know what’s in the store and where it us. Otherwise, shopper journeys aren’t interesting. Unfortunately, that knowledge is often scarce in the retail enterprise – and there’s often no institutional memory. So even … Continue reading "Creating an Institutional Memory of the Store Layout"
We’ve recently been using a data visualization focused on measuring the intra-day impact of shopper to labor ratios on conversion in the store that’s worth a look. Why is STARS data important? It’s one of the best and most direct uses of shopper journey data- an intra-day STARs analysis can significantly improve labor models. … Continue reading "The STARs Clock: A Data Visualization for Associate Optimization"
The Measurement Minute by Gary Angel The traditional measure used to optimize space in store layout is sales per square foot. Optimizing sales per square foot doesn’t mean that the merchandise with the highest sales should have the most square feet. Some merchandise doesn’t need a lot of space. Some does. The important metric … Continue reading "Density Metrics and Store Layout Optimization"
The Measurement Minute by Gary Angel Self-selection makes understanding optimal store layout challenging. Using measures of independence, you can get a strong sense of how dependent a merchandising section is on its placement in the store. This lets you target layout experimentation into places that are likely to significantly impact store performance. Not only … Continue reading "Measures of Dependence in Retail – Understanding Self-Selection and Store Layout"
The Measurement Minute by Gary Angel For shopper measurement, self-selection introduces massive biases in behavioral data. Different shopper populations behave differently not because of what we do or how the store works, but simply because they have different intent. When two stores perform differently, it may be because one store is better than the … Continue reading "In-Store Shopper Metrics: Dependence and Independence"