The Cloudera Data Platform (CDP) has reduced NEW YORKER’s number of out-of-stock situations, improving the availability of products in store and customer satisfaction.
Stock is allocated to stores where there is demand, removing the need to reduce the price on items and increasing profitability.
Orders placed with suppliers are more optimized to meet customer demand.
NEW YORKER is a German-based clothing retailer and one of the world’s largest international fashion brands. With over 1,100 retail stores across 47 countries and 21,000 employees, it provides young audiences with affordable fashion.
Staying Ahead of Tomorrow’s Trends
Stockouts – the unavailability of specific items or products at the point of purchase when the customer is ready to buy – cost retailers an estimated $1 trillion every year.
In retail fashion, staying ahead of the latest trends is key to customer engagement. As a competitive industry, retailers rarely disclose their methods of giving the customer what they want to guarantee sales. What makes NEW YORKER special is that every year its buyers manage without fail to catch the big trends. As a result, the retailer consistently delivers strong year-on-year results.
The types of data important to NEW YORKER come from its enterprise resources planning (ERP) system – with sales, pricing, supplier orders, product information and logistics providing insight.
To enhance its operations and maintain its position as an industry vanguard, NEW YORKER’s team of 27 data scientists, data engineers, DevOps engineers and product owners worked with Cloudera to better harness the vast amounts of data already at the retailer’s fingertips. Adopting the Cloudera Data Platform (CDP), NEW YORKER’s aim was to advance the quintessential retail fashion use cases: pricing, order optimization, demand forecasting and distribution.
Anticipating customer needs for a better in-store experience
CDP has helped the retailer become a more data-driven business. Having all its data in one place and easily accessible via a data lakehouse means data silos are eliminated, enabling NEW YORKER to run large queries and programmes to extract further value.
As an example, with CDP’s insights, customers are now more likely to find the right size of item in store, resulting in fewer out-of-stock situations. It’s a win-win scenario: customers get the exact item they want, and the retailer records more sales.
The data lakehouse also means NEW YORKER can quickly process and explore data even with very large database tables. Now, the retailer can see the distribution of data and how it looks – including identifying outliers at a glance.
Outliers can cause serious problems in statistical analyses. With CDP’s versatility, the data science team can hone its analysis with a variety of tools to tackle outlier detection and data quality issues.
Working towards identifying the data that isn’t there
A year on from the platform’s implementation, NEW YORKER has reduced the number of out-of-stock situations and improved product availability in store.
As a brick-and-mortar retailer without an online sales platform, weather data is important to NEW YORKER’s operations. Here, its seasonal view is an industry benchmark, going beyond identifying the selling of umbrellas on rainy days to recognizing local phenomena. For example, men, unlike women, are less likely to shop in advance to prepare for seasonal changes, so this will lead to a spike in male swimwear sales on a blistering hot day. Armed with such insight, the retailer can adjust its stock on the shop floor accordingly to capitalise on demand.
Hosting NEW YORKER’s distribution system on CDP has made it more reliable, scalable, faster, and ready for further expansion. Regardless of how fast NEW YORKER grows, it can be sure that CDP will not become a bottleneck. It also means the retailer can develop machine learning-driven optimizations going forward.
Over the next year, NEW YORKER is working on a range of use cases it plans to bring into production. Some are already in play, including pricing, further advancement on order optimization, and logistics for a more efficient supply chain.