{"id":2346,"date":"2024-03-14T11:46:37","date_gmt":"2024-03-14T11:46:37","guid":{"rendered":"https:\/\/www.footfallcam.com\/blog\/?p=2346"},"modified":"2025-11-04T07:34:09","modified_gmt":"2025-11-04T07:34:09","slug":"redefining-queue-analytics-a-big-data-modelling-approach","status":"publish","type":"post","link":"https:\/\/www.footfallcam.com\/blog\/2024\/03\/redefining-queue-analytics-a-big-data-modelling-approach\/","title":{"rendered":"Redefining Queue Analytics: A Big Data Modelling Approach"},"content":{"rendered":"\n<div style=\"height:20px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<p><span style=\"font-family: archivo, sans-serif;\"><span style=\"color: #666666;\">Queue analytics is a key metric to understanding customer satisfaction in various industries, such as fast food restaurants<\/span><span style=\"color: #166bff;\"><a style=\"color: #166bff;\" href=\"https:\/\/www.footfallcam.com\/Industries\/FastFoodRestaurant\" target=\"_blank\" rel=\"noopener\">[1]<\/a><\/span><span style=\"color: #666666;\">, supermarkets<\/span><span style=\"color: #166bff;\"><a style=\"color: #166bff;\" href=\"https:\/\/www.footfallcam.com\/Industries\/Supermarkets\" target=\"_blank\" rel=\"noopener\">[2]<\/a><\/span>\u00a0<span style=\"color: #666666;\">and airports<\/span><span style=\"color: #166bff;\"><a style=\"color: #166bff;\" href=\"https:\/\/www.footfallcam.com\/Industries\/Airports\" target=\"_blank\" rel=\"noopener\">[3]<\/a><\/span><span style=\"color: #666666;\">. Business operators are in dire need for\u00a0<em>real-time data<\/em> on customer flow and queue wait durations, so that they can optimise on the number of service cashiers required, service SOP and cashier trainings. A satisfied customer is a customer who does not need to wait too long in a queue to checkout.<\/span><\/span><\/p>\n<p>\u00a0<\/p>\n<p><span style=\"font-family: archivo, sans-serif; color: #666666;\">By understanding and responding to customer behaviour patterns, business can significantly enhance the shopping experience, leading to increased customer satisfaction, loyalty, and ultimately, profitability. This aligns with the overarching business need to create a seamless and positive customer journey, which is integral in today\u2019s competitive business landscape.<\/span><\/p>\n<p>\u00a0<\/p>\n<p><span style=\"font-family: archivo, sans-serif; color: #666666;\">In the current market, there are plenty of sensor-based queue analytics solutions to track customer journey in a queue. For example, FootfallCam 3D Pro2 is a\u00a0<strong>stereo vision camera system<\/strong>\u00a0mounted on the ceiling, that does customer detection, tracking and queue counting,\u00a0<em>all in a single\u00a0<\/em>device.<\/span><\/p>\n\n\n\n<div style=\"height:50px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<h3 class=\"article-h2 article-h3\"><span style=\"font-family: archivo, sans-serif; font-size: 28px; color: #323232;\">Current Challenges<\/span><\/h3>\n\n\n\n<div style=\"height:20px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<p><span style=\"font-family: archivo, sans-serif;\"><span style=\"color: #666666;\">Although the FootfallCam 3D Pro2 achieves the highest-in-class 99% counting accuracy<\/span><span style=\"color: #166bff;\"><a style=\"color: #166bff;\" href=\"https:\/\/www.footfallcam.com\/blog\/2023\/10\/top-5-3d-people-counters-a-comprehensive-buying-guide\/\" target=\"_blank\" rel=\"noopener\">[4]<\/a><\/span><span style=\"color: #666666;\">, it is still not 100% accurate. In fact, there is no people counter with perfect counting accuracy, due to the dynamics of human behaviours in real life. For examples:<\/span><\/span><\/p>\n<ul>\n<li><span style=\"font-family: archivo, sans-serif; color: #666666;\">A customer leaves the trolley in the queue temporarily and goes out of the device coverage view<\/span><\/li>\n<li><span style=\"font-family: archivo, sans-serif; color: #666666;\">A customer bends down to grab point-of-sale merchandise or impulse buy items<\/span><\/li>\n<\/ul>\n\n\n\n<figure class=\"wp-block-image aligncenter size-full\"><img decoding=\"async\" loading=\"lazy\" class=\"alignnone wp-image-2352 size-full\" src=\"https:\/\/www.footfallcam.com\/blog\/wp-content\/uploads\/2023\/12\/Screenshot_2-1.png\" alt=\"\" width=\"959\" height=\"386\" srcset=\"https:\/\/www.footfallcam.com\/blog\/wp-content\/uploads\/2023\/12\/Screenshot_2-1.png 959w, https:\/\/www.footfallcam.com\/blog\/wp-content\/uploads\/2023\/12\/Screenshot_2-1-300x121.png 300w, https:\/\/www.footfallcam.com\/blog\/wp-content\/uploads\/2023\/12\/Screenshot_2-1-768x309.png 768w\" sizes=\"(max-width: 959px) 100vw, 959px\" \/><\/figure>\n<figure><\/figure>\n<figure class=\"wp-block-image aligncenter size-full\"><span style=\"font-family: archivo, sans-serif; color: #323232;\"><strong>Illustration of human behaviours in queues<\/strong><\/span><\/figure>\n\n\n\n<p>\u00a0<\/p>\n<p><span style=\"font-family: archivo, sans-serif; color: #666666;\">The result is that the duration of a customer waiting in the queue cannot be tracked continuously and effectively, and compromise the accuracy of average queue wait duration.<\/span><\/p>\n\n\n\n<div style=\"height:50px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<h3 class=\"article-h2 article-h3\"><span style=\"font-family: archivo, sans-serif; font-size: 28px; color: #323232;\">Rethinking Human Behaviours In Queues<\/span><\/h3>\n\n\n\n<div style=\"height:20px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<p><span style=\"font-family: archivo, sans-serif; color: #666666;\">To overcome the limitation, we have to rethink how customers queue up in a single queue, and how the average queue wait duration can be modelled from data statistics. Basically,<\/span><\/p>\n<ul>\n<li><span style=\"font-family: archivo, sans-serif; color: #666666;\">The first customer in the queue, who arrives at an empty service cashier, does not need to wait at all.<\/span><\/li>\n<li><span style=\"font-family: archivo, sans-serif; color: #666666;\">Subsequent customer needs to wait in the queue for as long as all the customers in front of him\/her have been served and leave the queue.<\/span><\/li>\n<li><span style=\"font-family: archivo, sans-serif; color: #666666;\">In other words, it is important to note\u00a0<em>how fast the service cashier serves the customers<\/em>, and\u00a0<em>how long is the queue<\/em>\u00a0at the moment when a customer joins the queue.<\/span><\/li>\n<\/ul>\n\n\n\n<div style=\"height:50px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<h3 class=\"article-h2 article-h3\"><span style=\"font-family: archivo, sans-serif; font-size: 28px; color: #323232;\">Innovative Data Modelling Approach<\/span><\/h3>\n\n\n\n<div style=\"height:20px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<p><span style=\"font-family: archivo, sans-serif;\"><span style=\"color: #666666;\">In an essence of Big Data analysis, we make use of Central Limit Theorem<\/span><a href=\"https:\/\/en.wikipedia.org\/wiki\/Central_limit_theorem\" target=\"_blank\" rel=\"noopener\"><span style=\"color: #166bff;\">[5]<\/span><\/a>\u00a0<span style=\"color: #666666;\">and Queue Theory<\/span><span style=\"color: #166bff;\"><a style=\"color: #166bff;\" href=\"https:\/\/en.wikipedia.org\/wiki\/Queueing_theory\" target=\"_blank\" rel=\"noopener\">[6]<\/a><\/span> <span style=\"color: #666666;\">to derive the average queue wait duration formula from first principles, guided by the queueing behaviour modelling above.<\/span><\/span><\/p>\n<p>\u00a0<\/p>\n\n\n\n<figure class=\"wp-block-image aligncenter size-full\"><img decoding=\"async\" loading=\"lazy\" class=\"alignnone wp-image-2357 size-full\" src=\"https:\/\/www.footfallcam.com\/blog\/wp-content\/uploads\/2023\/12\/Screenshot_3.png\" alt=\"\" width=\"635\" height=\"407\" srcset=\"https:\/\/www.footfallcam.com\/blog\/wp-content\/uploads\/2023\/12\/Screenshot_3.png 635w, https:\/\/www.footfallcam.com\/blog\/wp-content\/uploads\/2023\/12\/Screenshot_3-300x192.png 300w\" sizes=\"(max-width: 635px) 100vw, 635px\" \/><\/figure>\n\n\n\n<figure class=\"wp-block-image aligncenter size-full\"><img decoding=\"async\" loading=\"lazy\" class=\"alignnone wp-image-2356 size-full\" src=\"https:\/\/www.footfallcam.com\/blog\/wp-content\/uploads\/2023\/12\/Screenshot_1.png\" alt=\"\" width=\"468\" height=\"78\" srcset=\"https:\/\/www.footfallcam.com\/blog\/wp-content\/uploads\/2023\/12\/Screenshot_1.png 468w, https:\/\/www.footfallcam.com\/blog\/wp-content\/uploads\/2023\/12\/Screenshot_1-300x50.png 300w\" sizes=\"(max-width: 468px) 100vw, 468px\" \/><\/figure>\n<figure><\/figure>\n<figure><\/figure>\n<figure class=\"wp-block-image aligncenter size-full\"><span style=\"font-family: archivo, sans-serif; color: #323232;\"><strong>E(W) represents average queue wait duration, E(S) represents average queue serve duration, E(L) represents average queue length, P(L=0) represents the time probability where the queue is empty<\/strong><\/span><\/figure>\n<p>\u00a0<\/p>\n\n\n\n<p><span style=\"font-family: archivo, sans-serif; color: #666666;\">This revolutionary formula breaks free from the limitations and challenges raised above, because we do not need to track each individual queuing customers continuously. All we need is the queue serve duration and queue length data, both of which we can ensure high accuracy.<\/span><\/p>\n\n\n\n<div style=\"height:50px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<h3 class=\"article-h2 article-h3\"><span style=\"font-family: archivo, sans-serif; color: #323232; font-size: 28px;\">Results Comparison<\/span><\/h3>\n\n\n\n<div style=\"height:20px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<p><span style=\"font-family: archivo, sans-serif; color: #666666;\">We compare the average queue wait duration with the ground truth to validate our data model. The old approach is susceptible to the dynamics of human behaviours, while the new approach is a statistical modelling.<\/span><\/p>\n<p>\u00a0<\/p>\n<p><span style=\"font-family: archivo, sans-serif; color: #666666;\">This test is taken from 1-hour long data, with queue length being sampled every 5 seconds. There are 1000 customers queuing up naturally in this test.<\/span><\/p>\n<p>\u00a0<\/p>\n\n\n\n<figure class=\"wp-block-image aligncenter size-full\"><img decoding=\"async\" loading=\"lazy\" class=\"alignnone wp-image-2359 size-full\" src=\"https:\/\/www.footfallcam.com\/blog\/wp-content\/uploads\/2023\/12\/Screenshot_4.png\" alt=\"\" width=\"595\" height=\"368\" srcset=\"https:\/\/www.footfallcam.com\/blog\/wp-content\/uploads\/2023\/12\/Screenshot_4.png 595w, https:\/\/www.footfallcam.com\/blog\/wp-content\/uploads\/2023\/12\/Screenshot_4-300x186.png 300w\" sizes=\"(max-width: 595px) 100vw, 595px\" \/><\/figure>\n<figure><\/figure>\n<figure><\/figure>\n<figure class=\"wp-block-image aligncenter size-full\"><span style=\"font-family: archivo, sans-serif; color: #323232;\"><strong>Comparisons of different approaches with ground truth<\/strong><\/span><\/figure>\n<p>\u00a0<\/p>\n\n\n\n<p><span style=\"font-family: archivo, sans-serif; color: #666666;\">The results show that the new metric <strong>outperforms<\/strong> the old metric, improving from 99% to <strong>99.9%<\/strong> accuracy. The accuracy improvement is expected to be larger for harsher environments where device counting accuracy can be lower.<\/span><\/p>\n\n\n\n<div style=\"height:50px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<h3 class=\"article-h2 article-h3\"><span style=\"font-family: archivo, sans-serif; color: #323232; font-size: 28px;\">Conclusion<\/span><\/h3>\n\n\n\n<div style=\"height:20px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<p><span style=\"font-family: archivo, sans-serif; color: #666666;\">This is a showcase of using modern data-driven statistical approach to tackle an age-old problem in queue analytics. This will help all industries to better measure the\u00a0<strong>customer satisfaction<\/strong>,\u00a0<strong>service cashier KPI<\/strong>\u00a0as well as to surface any\u00a0<strong>operational inefficiency<\/strong>.<\/span><\/p>\n<p>\u00a0<\/p>\n<p><span style=\"font-family: archivo, sans-serif; color: #666666;\">With better data metrics and visibility, businesses can now reduce cost and increase sales more effectively.<\/span><\/p>\n\n\n\n<div style=\"height:50px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<hr \/>\n<h3><span style=\"font-family: archivo, sans-serif; color: #323232;\">FAQs :<\/span><\/h3>\n\n\n\n<div style=\"height:20px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<p><span style=\"font-family: archivo, sans-serif; color: #323232;\"><strong>1. Which devices support this new metric for average queue wait duration?<\/strong><\/span><\/p>\n<p><span style=\"font-family: archivo, sans-serif;\"><span style=\"color: #666666;\">All the devices which have the Queue Counting feature, support this new metric for a more accurate average queue wait duration. The devices include FootfallCam<\/span>\u00a0<span style=\"color: #166bff;\"><a style=\"color: #166bff;\" href=\"https:\/\/www.footfallcam.com\/Product\/FootfallCam-3D-Pro2\" target=\"_blank\" rel=\"noopener\">3D Pro2<\/a><\/span><span style=\"color: #666666;\">,<\/span>\u00a0<span style=\"color: #166bff;\"><a style=\"color: #166bff;\" href=\"https:\/\/www.footfallcam.com\/Product\/FootfallCam-3D-ProWave\" target=\"_blank\" rel=\"noopener\">3D Prowave<\/a><\/span><span style=\"color: #666666;\">,<\/span>\u00a0<span style=\"color: #166bff;\"><a style=\"color: #166bff;\" href=\"https:\/\/www.footfallcam.com\/Product\/FootfallCam-3D-Extend\" target=\"_blank\" rel=\"noopener\">3D Extend<\/a><\/span>\u00a0<span style=\"color: #666666;\">and<\/span>\u00a0<span style=\"color: #166bff;\"><a style=\"color: #166bff;\" href=\"https:\/\/www.footfallcam.com\/Product\/FootfallCam-Centroid\" target=\"_blank\" rel=\"noopener\">Centroid<\/a><\/span><span style=\"color: #666666;\">.<\/span> <span style=\"color: #666666;\">Kindly contact<\/span> <span style=\"color: #166bff;\"><a style=\"color: #166bff;\" href=\"mailto:sales@footfallcam.com\" target=\"_blank\" rel=\"noopener\">sales@footfallcam.com<\/a><\/span><span style=\"color: #666666;\">.<\/span><\/span><\/p>\n<p>\u00a0<\/p>\n<p><span style=\"font-family: archivo, sans-serif; color: #323232;\"><strong>2. Can I have both the old and new metrics at the same time?<\/strong><\/span><\/p>\n<p><span style=\"font-family: archivo, sans-serif; color: #666666;\">Absolutely, however we strongly encourage using the new metric for its superior accuracy.<\/span><\/p>\n\n\n\n<div style=\"height:30px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<hr \/>\n<p><span style=\"font-family: archivo, sans-serif; color: #666666;\">References:<\/span><\/p>\n<ol>\n<li><span style=\"font-family: archivo, sans-serif;\"><span style=\"color: #666666;\">\u201c<\/span><span style=\"color: #166bff;\"><a style=\"color: #166bff;\" href=\"https:\/\/www.footfallcam.com\/Industries\/FastFoodRestaurant\" target=\"_blank\" rel=\"noopener\">Fast Food Restaurants Queue Counting<\/a><\/span><span style=\"color: #666666;\">\u201c.\u00a0<em>by FootfallCam<\/em>.<\/span><\/span><\/li>\n<li><span style=\"font-family: archivo, sans-serif;\"><span style=\"color: #666666;\">\u201c<\/span><span style=\"color: #166bff;\"><a style=\"color: #166bff;\" href=\"https:\/\/www.footfallcam.com\/Industries\/Supermarkets\" target=\"_blank\" rel=\"noopener\">Supermarkets Queue Counting<\/a><\/span><span style=\"color: #666666;\">\u201c.\u00a0<em>by FootfallCam<\/em>.<\/span><\/span><\/li>\n<li><span style=\"font-family: archivo, sans-serif;\"><span style=\"color: #666666;\">\u201c<\/span><span style=\"color: #166bff;\"><a style=\"color: #166bff;\" href=\"https:\/\/www.footfallcam.com\/Industries\/Airports\" target=\"_blank\" rel=\"noopener\">Airports Queue Counting<\/a><\/span><span style=\"color: #666666;\">\u201c.\u00a0<em>by FootfallCam<\/em>.<\/span><\/span><\/li>\n<li><span style=\"font-family: archivo, sans-serif;\"><span style=\"color: #666666;\"><em>\u201c<\/em><\/span><span style=\"color: #166bff;\"><a style=\"color: #166bff;\" href=\"https:\/\/www.footfallcam.com\/blog\/2023\/10\/top-5-3d-people-counters-a-comprehensive-buying-guide\/\" target=\"_blank\" rel=\"noopener\">Top 5 3D People Counters<\/a><\/span><em><span style=\"color: #666666;\">\u201c.<\/span> <span style=\"color: #666666;\">by FootfallCam<\/span><\/em><span style=\"color: #666666;\">.<\/span><\/span><\/li>\n<li><span style=\"font-family: archivo, sans-serif;\"><span style=\"color: #666666;\">\u201c<\/span><span style=\"color: #166bff;\"><a style=\"color: #166bff;\" href=\"https:\/\/en.wikipedia.org\/wiki\/Central_limit_theorem\" target=\"_blank\" rel=\"noopener\">Central Limit Theorem<\/a><\/span><span style=\"color: #666666;\">\u201c.\u00a0<em>by Wikipedia<\/em>.<\/span><\/span><\/li>\n<li><span style=\"font-family: archivo, sans-serif;\"><span style=\"color: #666666;\">\u201c<\/span><span style=\"color: #166bff;\"><a style=\"color: #166bff;\" href=\"https:\/\/en.wikipedia.org\/wiki\/Queueing_theory\" target=\"_blank\" rel=\"noopener\">Queueing Theory<\/a><\/span><span style=\"color: #666666;\">\u201c.\u00a0<em>by Wikipedia<\/em>.<\/span><\/span><\/li>\n<\/ol>\n","protected":false},"excerpt":{"rendered":"<p>Queue analytics is a key metric to understanding customer satisfaction in various industries, such as fast food restaurants[1], supermarkets[2]\u00a0and airports[3]. Business operators are in dire need for\u00a0real-time data on customer &#8230;<\/p>\n","protected":false},"author":1,"featured_media":2322,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":"[]"},"categories":[719,189,722],"tags":[31,420,260,421,28,27,25,411,250,419,291],"_links":{"self":[{"href":"https:\/\/www.footfallcam.com\/blog\/wp-json\/wp\/v2\/posts\/2346"}],"collection":[{"href":"https:\/\/www.footfallcam.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.footfallcam.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.footfallcam.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.footfallcam.com\/blog\/wp-json\/wp\/v2\/comments?post=2346"}],"version-history":[{"count":37,"href":"https:\/\/www.footfallcam.com\/blog\/wp-json\/wp\/v2\/posts\/2346\/revisions"}],"predecessor-version":[{"id":7115,"href":"https:\/\/www.footfallcam.com\/blog\/wp-json\/wp\/v2\/posts\/2346\/revisions\/7115"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.footfallcam.com\/blog\/wp-json\/wp\/v2\/media\/2322"}],"wp:attachment":[{"href":"https:\/\/www.footfallcam.com\/blog\/wp-json\/wp\/v2\/media?parent=2346"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.footfallcam.com\/blog\/wp-json\/wp\/v2\/categories?post=2346"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.footfallcam.com\/blog\/wp-json\/wp\/v2\/tags?post=2346"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}