Skip to content 
Samworth Brothers
AI for packaging and logistics
Reducing food waste through a predictive solution for package sizing and logistics.
Key results and metrics
Samworth Brothers' challenge
Samworth Brothers is the largest British food manufacturer, producing a range of chilled and ambient foods, both own-label and branded. They have a number of subsidiaries and complex operations that produce and stock food for millions of customers.
The stock department would receive frequent signals from client supermarkets that a significant amount of food was wasted. The reason lay in packaging and delivery constraints, such as box and vehicle sizes.
The issues caused:
- A drop in orders;
- Low predictability of sales and stock demand;
- Negative impact on sustainability commitments and food waste targets.
Samworth Brothers (SB) had access to large volumes of data shared by supermarkets. They were looking to use this data and leverage AI to determine how products were selling and when food was wasted.
However, they lacked the capacity to build a solution that could proactively tell them how to package food to optimise the volume of sales while minimising food waste.
The solution
Strategy
We strategised a way to package food in a way that better fit demand on various days. We set out by analysing logistics operations and raising key questions like:
- How do store operators know how many boxes of X product to order?
- Why does demand tend to go up or down? Is it affected by factors like the weather or the day of the week?
- What are the most common problems that logistics operators face?
To find the answers, we deployed a team of data product consultants and business analysts who interviewed various stakeholders. This helped us determine that the core challenge lay in having a better variety of box sizes and a better approach to stocking delivery vehicles with boxes.
This would all be enabled by more sophistication in forecasting how much food should be ordered on any given day.
Implementation
Infinite Lambda’s team of data engineers, data scientists, and MLOps experts built a complete solution using Snowflake.
The pipelines we built would ingest all relevant data into Snowflake, bringing data from all sources into a singular data model that data scientists can leverage. This contributes to ease of use but also improves the confidence in the overall quality of the data.
Infinite Lambda’s data scientists then worked with client stakeholders to conduct simulations and experiments that determine optimal box sizes and set out packaging instructions for vehicle operators.
The data scientists then built a dashboard that surfaced forecasts on how much food is likely to be ordered by any given store, and how it should be packaged.
The result
Having powerful forecasting capabilities, Samworth Brothers started leveraging the insights to improve packaging and logistics.
As a result, they have reduced food waste by an impressive 23% according to initial measurements.
We continue to collaborate with the client to further optimise logistics and manufacturing operations.
Let’s walk the walk together
Our data expertise translates into cutting-edge, modular solutions that empower people and help organisations thrive in the era of AI.
see Related Stories
We work with modern organisations to strategise and build cutting-edge solutions, help them adopt data & AI innovation, and nurture key competencies for scaling in the long run.