Fast fashion retailer cut overstock by 50%
Use Case
Demand forecasting
A major global retailer with omnichannel distribution of over 10K SKUs was struggling to meet unusual consumer demand. Customers were unexpectedly active in new seasonal patterns, and demand varied greatly across different regions and stores. This level of variability meant that the company’s typical methods of predicting demand were no longer granular nor accurate enough. The company was experiencing:
- Loss of sales from bestseller stockouts, despite product availability in other locations
- High overstock expenses from inventory holding, obsolescence, and reverse logistics
- Low margins due to inefficient and reactive promotions and end-of-season sales
Fortunately, Pecan’s predictive models provided results, including a reduction of up to 50% in overstock amounts and an uplift of 10-25% in sales due to increased product availability.
Industry: Fast fashion
Company Size: Nearly 5K stores around the world and over $23B revenue in 2021
Solution: Alignment of inventory with demand to reduce overstock expenses
Platform Use Case: Demand forecastingDemand forecasting involves trying to determine the likely future need for an item, based on historical data and analytics showing how much of it has…
Data Stack: SAP HANA
50%
reduction in overstock amounts
10-25%
80-95%
Challenge
Aggressive discounting kept up with fast fashion, but slowed profits
Traditional forecasting methods made it almost impossible for the retailer to ensure that supply at stores met consumer demand. This mismatch resulted in sub-optimal financial performance and a mediocre customer experience.
The inability to accurately forecast demand at both store and SKU levels led to significant revenue losses because of stockouts, lower margins due to aggressive discounts, and overall high operational costs related to inventory holding and reverse logistics.
Solution
SKU-level predictions to forecast demand at the speed of shopping
Pecan’s forecasting models generated sales forecasts at a granular level on a per-SKU, per-week/day, and per-store basis. With the Pecan platform, the retailer was empowered to build models that integrated past transactional (sales/usage) data, operational data, inventory data, and external data enrichments provided by Pecan.
Traditional methods used to deal with inventory gaps hadn’t shown results, but Pecan’s predictive approach helped the retailer align inventory levels so they met actual customer demand.
Results
Reducing overstock and boosting sales
Using Pecan’s detailed demand forecasts, the retailer saw a reduction of up to 50% in overstock amounts. The alignment of inventory and demand also meant they soon achieved 10-25% additional sales, thanks to fewer stockouts. Pecan’s sales prediction modelIn the context of machine learning, a model is a specific instance or example of an algorithm that has been created based on a particular… demonstrated an ongoing precision rate of 80-95% — an impressive result in any circumstances, but especially amid the volatility this retailer experienced.
With Pecan’s predictions in hand, both the retail leadership and customers achieved their goal of keeping up with the latest in fashion.
Contents
It’s time to refine your outreach with customer foresight
Latest Resources
10 Data Breakthroughs That Solve Business Problems
Are you curious about your enterprise and how you can improve your business? Meet our latest Data ScienceData science combines statistics, computer science, scientific methods, and business knowledge to analyze, model, and predict using data. The data science toolkit can be used... breakthroughs.
Predictive Analytics: Getting Actual Value from Machine Learning
In this webinar, we shared the essential components of predictive analyticsPredictive analytics uses data, statistics, and machine learning techniques to build mathematical models that can generate predictions about things likely to happen in the future.... to get value in the shortest time possible.
Stop User Churn in 3 Steps with Predictions
In a constant battle for user time, developers need to keep their users engaged and happy while monitoring reduced engagement and churn rates.