Burberry's Bold Fashion Marketing Transformation with IoT
Technology Category
- Analytics & Modeling - Machine Learning
- Infrastructure as a Service (IaaS) - Virtual Private Cloud
Applicable Industries
- Apparel
- Consumer Goods
Applicable Functions
- Sales & Marketing
Use Cases
- Clinical Image Analysis
- Time Sensitive Networking
Services
- System Integration
- Training
About The Customer
Burberry is a British luxury brand headquartered in London. Known for its bold, high-fashion apparel, Burberry uses thousands of images from multiple sources in its marketing campaigns. The company aims to capture the imagination, command attention, and win sales with its daring apparel. To do this effectively, Burberry needs to classify and annotate these valuable assets precisely. The company was already using Databricks, a single, unified analytics platform for all its stakeholders, and was looking for a solution that would integrate well with this existing system.
The Challenge
Burberry, a British luxury brand, faced a significant challenge in managing and annotating its thousands of marketing images. The company needed to classify these assets accurately to use them effectively in its marketing campaigns and drive the right action by the right audience. Burberry initially tried using an open-source tool for image annotation, but it had serious drawbacks. The company was looking for a solution that could improve the data for training its models quickly and easily. They wanted to produce labels for thousands of images and place them seamlessly into a model development pipeline for convenient reuse. The challenge was to find a solution that would integrate well with Burberry's existing Databricks implementation, a single, unified analytics platform for all its stakeholders.
The Solution
Burberry implemented Labelbox within its Databricks Lakehouse Platform environment to efficiently annotate its marketing assets. Labelbox was chosen due to its tight integration with Databricks and its customer-centric purchase process. The implementation process was straightforward, with Burberry importing images to Labelbox from their Amazon S3 bucket via API. Once Labelbox was officially selected, Burberry connected it to the company's core virtual private cloud and S3, treating images just like any other data set within its Databricks Lakehouse Platform. The solution was up and running within a month for the data science team members, and business and marketing users were also onboarded expediently. Burberry continues to rely on Databricks Unity Catalog to keep data secure and comply with data privacy regulations.
Operational Impact
Quantitative Benefit
Case Study missing?
Start adding your own!
Register with your work email and create a new case study profile for your business.
Related Case Studies.
Case Study
Fire Alarm System and Remote Monitoring Sytem
Fire alarm systems are essential in providing an early warning in the event of fire. They help to save lives and protect property whilst also fulfilling the needs of insurance companies and government departments.Fire alarm systems typically consist of several inter-linked components, such as smoke detectors, heat detector, carbon monoxide, manual call points, sounders, alarm and buzzer. The fire alarm system should give immediate information in order to prevent the fire spread and protect live and property.To get maximum protection a shoe manufacturer in Indonesia opted for a new fire alarm system to monitor 13 production sites spread over 160 hectars. Although the company had an existing fire alarm system, it could not be monitored remotely.It was essential that the new system would be able to be monitored from a central control room. It needed to be able to connect to the existing smoke detector and manual call point. Information should be easily collected and passed on to the Supervisory Control and Data Acquisition (SCADA) system. Furthermore, the system should have several features such as alarm management, auto reporting, being connected to many client computers without additional cost, and run 24/7 without fails. The company also needed a system which could be implemented without changing the architecture of the existing fire alarm system.
Case Study
IoT Applications and Upgrades in Textile Plant
At any given time, the textile company’s manufacturing facility has up to 2,000 textile carts in use. These carts are pushed from room to room, carrying materials or semi-finished products. Previously, a paper with a hand-written description was attached to each cart. This traditional method of processing made product tracking extremely difficult. Additionally, making sure that every cart of materials or semi-finished products went to its correct processing work station was also a problem. Therefore, the company desired an intelligent solution for tracking assets at their factories. They also wanted a solution that would help them collect process data so they could improve their manufacturing efficiency.
.png)
Case Study
Improving Vending Machine Profitability with the Internet of Things (IoT)
The vending industry is undergoing a sea change, taking advantage of new technologies to go beyond just delivering snacks to creating a new retail location. Intelligent vending machines can be found in many public locations as well as company facilities, selling different types of goods and services, including even computer accessories, gold bars, tickets, and office supplies. With increasing sophistication, they may also provide time- and location-based data pertaining to sales, inventory, and customer preferences. But at the end of the day, vending machine operators know greater profitability is driven by higher sales and lower operating costs.
Case Study
Series Production with Lot-size-1 Flexibility
Nobilia manufactures customized fitted kitchens with a lot size of 1. They require maximum transparency of tracking design data and individual processing steps so that they can locate a particular piece of kitchen furniture in the sequence of processes.
Case Study
Retailer Uses RFID Scanner to Improve Efficiency
Patrizia Pepe wished to improve the logistics of their warehouse: accepting incoming goods from their production sites, movement of items throughout
the warehouse, and packaging of goods for distribution to the retail locations. They initially tried to use barcodes for this function. Because barcodes must be individually scanned within a line-of-sight, the acceptance of goods coming into the warehouse was too time consuming. Working with the University of Florence, Patrizia Pepe instituted a five-month pilot project beginning in August of 2009 to test the validity of an RFID solution. The pilot involved tagging of about 60,000 items for the second seasonal collection, and convinced the company to move forward with tagging all items.
