Machine Learning in Supply Chain: the case study of Plum Living’s Inventory transformation

Machine learning is increasingly shaping modern Supply Chain strategies, yet many companies still question its real operational impact. Beyond promises and theory, decision-makers want concrete proof: real use cases, measurable results, and practical lessons they can apply to their own Supply Chain operations.

This machine learning in Supply Chain case study explores how Plum Living, a fast-growing European interior design brand, transformed its inventory management using AI-driven Supply Chain planning. It offers a clear, real-life example of how machine learning can move organizations from manual planning to data-driven decision-making.

By downloading this case study, you will discover how machine learning helps regain control over inventory while supporting scalable growth.

The Supply Chain challenges behind rapid growth

Founded in Paris in 2020, Plum Living experienced rapid growth thanks to its digital-first model and customized products. However, this growth quickly exposed structural Supply Chain limitations. Inventory planning relied heavily on Excel spreadsheets, making it difficult to anticipate demand, manage suppliers, and maintain optimal stock levels.

Like many mid-sized companies, Plum Living faced recurring Supply Chain challenges:

• limited demand visibility
• growing inventory levels and long lead times
• manual replenishment decisions
• lack of coordination with suppliers

These issues increased operational pressure and constrained the company’s ability to scale efficiently across Europe.

How machine learning transformed Supply Chain planning

To address these challenges, Plum Living turned to Flowlity’s AI-powered platform, designed to automate and optimize Supply Chain planning through machine learning. The goal was not to replace planners, but to enhance decision-making with reliable forecasts and actionable recommendations.

Using machine learning Supply Chain forecasting, demand patterns were analyzed and translated into probabilistic forecasts. This allowed teams to simulate scenarios, anticipate variability, and adjust inventory levels accordingly.

Within weeks, Plum Living was able to:

• automate replenishment recommendations
• build a 9-month Supply Chain plan across two warehouses
• improve collaboration with suppliers through shared visibility
• reduce manual planning efforts

Machine learning enabled a shift from reactive planning to continuous, data-driven Supply Chain management.

Measurable results from machine learning in Supply Chain forecasting

This machine learning in Supply Chain case study highlights tangible business outcomes, not just technical implementation. After go-live, Plum Living achieved measurable improvements:

• 21% reduction in inventory value, freeing up working capital
• fewer days of stock on hand
• streamlined replenishment processes through automation
• improved operational control across the Supply Chain

These results demonstrate how machine learning can directly impact inventory performance, service levels, and Supply Chain resilience.

What you will learn in this Supply Chain case study

This case study is designed for Supply Chain Directors, Demand Planners, COOs, and Operations leaders looking for practical insights rather than theory. By downloading it, you will learn:

• how to transition from Excel-based planning to AI-driven Supply Chain forecasting
• how machine learning supports inventory optimization without added complexity
• what implementation timelines really look like
• which KPIs matter most to measure Supply Chain performance

The content focuses on real decisions, real constraints, and real outcomes.

Download the Machine Learning Supply Chain case study

If you are exploring machine learning to improve Supply Chain planning and inventory performance, this case study provides concrete proof of value. Plum Living’s experience shows how AI can reduce inventory, improve visibility, and support sustainable growth.

👉 Download the full Machine Learning Supply Chain case study to explore the complete journey, from initial challenges to measurable business results.

‍